<!DOCTYPE html><html xmlns:cc="http://creativecommons.org/ns#"><head prefix="og: http://ogp.me/ns# fb: http://ogp.me/ns/fb# medium-com: http://ogp.me/ns/fb/medium-com#"><meta http-equiv="Content-Type" content="text/html; charset=utf-8"><meta name="viewport" content="width=device-width, initial-scale=1"><title>Hurricane Harvey InsurTech Case Study; visual intelligence is transforming claim response times.</title><link rel="canonical" href="https://towardsdatascience.com/hurricane-harvey-insurtech-case-study-visual-intelligence-is-transforming-claim-response-times-3275042fbd8d"><meta name="title" content="Hurricane Harvey InsurTech Case Study; visual intelligence is transforming claim response times."><meta name="referrer" content="unsafe-url"><meta name="description" content="Storms of unprecedented power have lashed the United States and the Caribbean over the past few weeks, leaving a trail of devastation estimated in the tens of billions of dollars. The US alone has…"><meta name="theme-color" content="#000000"><meta property="og:title" content="Hurricane Harvey InsurTech Case Study; visual intelligence is transforming claim response times."><meta property="og:url" content="https://towardsdatascience.com/hurricane-harvey-insurtech-case-study-visual-intelligence-is-transforming-claim-response-times-3275042fbd8d"><meta property="og:image" content="https://cdn-images-1.medium.com/max/1200/1*lSrjjYyG8X2ND8hFmjBtAA.png"><meta property="fb:app_id" content="542599432471018"><meta property="og:description" content="Storms of unprecedented power have lashed the United States and the Caribbean over the past few weeks, leaving a trail of devastation…"><meta name="twitter:description" content="Storms of unprecedented power have lashed the United States and the Caribbean over the past few weeks, leaving a trail of devastation…"><meta name="twitter:image:src" content="https://cdn-images-1.medium.com/max/1200/1*lSrjjYyG8X2ND8hFmjBtAA.png"><link rel="publisher" href="https://plus.google.com/103654360130207659246"><link rel="author" href="https://towardsdatascience.com/@raldon"><meta property="author" content="Rafael Aldon"><meta property="og:type" content="article"><meta name="twitter:card" content="summary_large_image"><meta property="article:publisher" content="https://www.facebook.com/towardsdatascience"><meta property="article:author" content="https://towardsdatascience.com/@raldon"><meta name="robots" content="index, follow"><meta property="article:published_time" content="2017-09-20T01:29:31.504Z"><meta name="twitter:site" content="@TDataScience"><meta property="og:site_name" content="Towards Data Science"><meta name="twitter:label1" value="Reading time"><meta name="twitter:data1" value="7 min read"><meta name="twitter:app:name:iphone" content="Medium"><meta name="twitter:app:id:iphone" content="828256236"><meta name="twitter:app:url:iphone" content="medium://p/3275042fbd8d"><meta property="al:ios:app_name" content="Medium"><meta property="al:ios:app_store_id" content="828256236"><meta property="al:android:package" content="com.medium.reader"><meta property="al:android:app_name" content="Medium"><meta property="al:ios:url" content="medium://p/3275042fbd8d"><meta property="al:android:url" content="medium://p/3275042fbd8d"><meta property="al:web:url" content="https://towardsdatascience.com/hurricane-harvey-insurtech-case-study-visual-intelligence-is-transforming-claim-response-times-3275042fbd8d"><link rel="search" type="application/opensearchdescription+xml" title="Medium" href="/osd.xml" /><link rel="alternate" href="android-app://com.medium.reader/https/medium.com/p/3275042fbd8d" /><script type="application/ld+json">{"@context":"http://schema.org","@type":"NewsArticle","image":{"@type":"ImageObject","width":940,"height":627,"url":"https://cdn-images-1.medium.com/max/1880/1*lSrjjYyG8X2ND8hFmjBtAA.png"},"datePublished":"2017-09-20T01:29:31.504Z","dateModified":"2018-01-25T04:27:02.206Z","headline":"Hurricane Harvey InsurTech Case Study; visual intelligence is transforming claim response times.","name":"Hurricane Harvey InsurTech Case Study; visual intelligence is transforming claim response times.","keywords":["Hurricane Harvey","Insurance","Machine Learning","Big Data","Towards Data Science"],"author":{"@type":"Person","name":"Rafael Aldon","url":"https://towardsdatascience.com/@raldon"},"creator":["Rafael Aldon"],"publisher":{"@type":"Organization","name":"Towards Data Science","url":"https://towardsdatascience.com","logo":{"@type":"ImageObject","width":215,"height":60,"url":"https://cdn-images-1.medium.com/max/430/1*5ztbgEt4NqpVaxTc64C-XA.png"}},"mainEntityOfPage":"https://towardsdatascience.com/hurricane-harvey-insurtech-case-study-visual-intelligence-is-transforming-claim-response-times-3275042fbd8d"}</script><link rel="stylesheet" href="https://cdn-static-1.medium.com/_/fp/css/main-branding-base.JJK6HvzwD6aPPTmAOMcmoQ.css"><script>if (window.top !== window.self) window.top.location = window.self.location.href;var OB_startTime = new Date().getTime(); var OB_loadErrors = []; function _onerror(e) { OB_loadErrors.push(e) }; if (document.addEventListener) document.addEventListener("error", _onerror, true); else if (document.attachEvent) document.attachEvent("onerror", _onerror); function _asyncScript(u) {var d = document, f = d.getElementsByTagName("script")[0], s = d.createElement("script"); s.type = "text/javascript"; s.async = true; s.src = u; f.parentNode.insertBefore(s, f);}function _asyncStyles(u) {var d = document, f = d.getElementsByTagName("script")[0], s = d.createElement("link"); s.rel = "stylesheet"; s.href = u; f.parentNode.insertBefore(s, f); return s}(new Image()).src = "/_/stat?event=pixel.load&origin=" + encodeURIComponent(location.origin);</script><script>window.ga=window.ga||function(){(ga.q=ga.q||[]).push(arguments)};ga.l=+new Date; ga("create", "UA-24232453-2", "auto", {"allowLinker": true, "legacyCookieDomain": window.location.hostname}); ga("send", "pageview");ga("create", "UA-19707169-24", "auto", 'tracker0'); ga("tracker0.send", "pageview");</script><script async src="https://www.google-analytics.com/analytics.js"></script><script>(function () {var height = window.innerHeight || document.documentElement.clientHeight || document.body.clientHeight; var width = window.innerWidth || document.documentElement.clientWidth || document.body.clientWidth; document.write("<style>section.section-image--fullBleed.is-backgrounded {padding-top: " + Math.round(1.1 * height) + "px;}section.section-image--fullScreen.is-backgrounded, section.section-image--coverFade.is-backgrounded {min-height: " + height + "px; padding-top: " + Math.round(0.5 * height) + "px;}.u-sizeViewHeight100 {height: " + height + "px !important;}.u-sizeViewHeight110 {height: " + Math.round(1.1 * height) + "px !important;}.u-sizeViewHeightMin100 {min-height: " + height + "px !important;}.u-sizeViewHeightMax100 {max-height: " + height + "px !important;}section.section-image--coverFade {height: " + height + "px;}.section-aspectRatioViewportPlaceholder, .section-aspectRatioViewportCropPlaceholder {max-height: " + height + "px;}.section-aspectRatioViewportBottomSpacer, .section-aspectRatioViewportBottomPlaceholder {max-height: " + Math.round(0.5 * height) + "px;}.zoomable:before {top: " + (-1 * height) + "px; left: " + (-1 * width) + "px; padding: " + height + "px " + width + "px;}</style>");})()</script><!--[if lt IE 9]><script charset="UTF-8" src="https://cdn-static-1.medium.com/_/fp/js/shiv.RI2ePTZ5gFmMgLzG5bEVAA.js"></script><![endif]--><link rel="icon" href="https://cdn-static-1.medium.com/_/fp/icons/favicon-rebrand-medium.3Y6xpZ-0FSdWDnPM3hSBIA.ico" class="js-favicon"><link rel="apple-touch-icon" sizes="152x152" href="https://cdn-images-1.medium.com/fit/c/304/304/1*F0LADxTtsKOgmPa-_7iUEQ.jpeg"><link rel="apple-touch-icon" sizes="120x120" href="https://cdn-images-1.medium.com/fit/c/240/240/1*F0LADxTtsKOgmPa-_7iUEQ.jpeg"><link rel="apple-touch-icon" sizes="76x76" href="https://cdn-images-1.medium.com/fit/c/152/152/1*F0LADxTtsKOgmPa-_7iUEQ.jpeg"><link rel="apple-touch-icon" sizes="60x60" href="https://cdn-images-1.medium.com/fit/c/120/120/1*F0LADxTtsKOgmPa-_7iUEQ.jpeg"><link rel="mask-icon" href="https://cdn-static-1.medium.com/_/fp/icons/monogram-mask.KPLCSFEZviQN0jQ7veN2RQ.svg" color="#171717"></head><body itemscope class=" postShowScreen v-glyph v-glyph--m2 v-enableBrandingButtons is-noJs"><script>document.body.className = document.body.className.replace(/(^|\s)is-noJs(\s|$)/, "$1is-js$2")</script><div class="site-main" id="container"><div class="butterBar butterBar--error"></div><div class="surface"><div id="prerendered" class="screenContent"><canvas class="canvas-renderer"></canvas><div class="container u-maxWidth740 u-xs-margin0 notesPositionContainer js-notesPositionContainer"></div><div class="metabar u-clearfix js-metabar u-textColorTransparentWhiteDarker u-fixed u-backgroundTransparentWhiteDarkest u-xs-sizeFullViewportWidth u-tintBgColor u-tintSpectrum"><div class="js-metabarMiddle metabar-inner u-marginAuto u-maxWidth1000 u-flexCenter u-justifyContentSpaceBetween u-height65 u-xs-height56 u-paddingLeft20 u-paddingRight20"><div class="metabar-block u-flex1  u-flexCenter"><div class="js-metabarLogoLeft"><a href="https://medium.com/" data-log-event="home" class="siteNav-logo u-flexCenter u-paddingTop0"><span class="svgIcon svgIcon--logoMonogram svgIcon--45px is-flushLeft u-textColorDarker"><svg class="svgIcon-use" width="45" height="45" viewBox="0 0 45 45" ><path d="M5 40V5h35v35H5zm8.56-12.627c0 .555-.027.687-.318 1.03l-2.457 2.985v.396h6.974v-.396l-2.456-2.985c-.291-.343-.344-.502-.344-1.03V18.42l6.127 13.364h.714l5.256-13.364v10.644c0 .29 0 .342-.185.528l-1.848 1.796v.396h9.19v-.396l-1.822-1.796c-.184-.186-.21-.238-.21-.528V15.937c0-.291.026-.344.21-.528l1.823-1.797v-.396h-6.471l-4.622 11.542-5.203-11.542h-6.79v.396l2.14 2.64c.239.292.291.37.291.768v10.353z"/></svg></span><span class="u-textScreenReader">Homepage</span></a></div><div class="u-alignMiddle u-inlineBlock u-verticalAlignTop u-height65 u-xs-height56"><div class="u-alignBlock"><span class="u-inlineBlock u-height28 u-xs-height24 u-verticalAlignTop u-marginRight20 u-marginLeft15 u-borderRightTransparentWhiteLighter"></span></div></div><div class="u-alignMiddle u-inlineBlock u-verticalAlignTop u-height65 u-xs-height56 u-marginRight18"><div class="u-alignBlock"><a class="js-collectionLogoOrName" href="https://towardsdatascience.com?source=logo-lo_Pde0GEfT2sEl---7f60cf5620c9"><span class="u-inlineBlock u-uiTextBold u-fontSize18 u-lineHeight18 u-xs-fontSize22 u-xs-lineHeight22 u-xs-noWrapWithEllipsis u-xs-maxWidth200">Towards Data Science</span></a></div></div><div class="u-alignMiddle u-inlineBlock u-verticalAlignTop u-height65 u-xs-height56 u-xs-hide"><div class="u-alignBlock"><div class="buttonSet"><button class="button button--primary button--smallest u-noUserSelect button--withChrome u-accentColor--buttonNormal js-relationshipButton is-smallPill"  data-action="sign-up-prompt" data-sign-in-action="toggle-follow-collection" data-requires-token="true" data-redirect="https://medium.com/_/subscribe/collection/towards-data-science" data-action-source="----7f60cf5620c9----------------------follow_header" data-collection-id="7f60cf5620c9"><span class="button-label  js-buttonLabel">Follow</span></button><a class="button button--light button--chromeless is-touchIconBlackPulse u-baseColor--buttonLight button--withIcon button--withSvgIcon"   href="https://twitter.com/TDataScience" title="Visit “Towards Data Science” on Twitter" aria-label="Visit “Towards Data Science” on Twitter" rel="me" target="_blank"><span class="button-defaultState"><span class="svgIcon svgIcon--twitterFilled svgIcon--25px"><svg class="svgIcon-use" width="25" height="25" viewBox="0 0 25 25" ><path d="M21.725 5.338c-.744.47-1.605.804-2.513 1.006a3.978 3.978 0 0 0-2.942-1.293c-2.22 0-4.02 1.81-4.02 4.02 0 .32.034.63.07.94-3.31-.18-6.27-1.78-8.255-4.23a4.544 4.544 0 0 0-.574 2.01c.04 1.43.74 2.66 1.8 3.38-.63-.01-1.25-.19-1.79-.5v.08c0 1.93 1.38 3.56 3.23 3.95-.34.07-.7.12-1.07.14-.25-.02-.5-.04-.72-.07.49 1.58 1.97 2.74 3.74 2.8a8.49 8.49 0 0 1-5.02 1.72c-.3-.03-.62-.04-.93-.07A11.447 11.447 0 0 0 8.88 21c7.386 0 11.43-6.13 11.414-11.414.015-.21.01-.38 0-.578a7.604 7.604 0 0 0 2.01-2.08 7.27 7.27 0 0 1-2.297.645 3.856 3.856 0 0 0 1.72-2.23"/></svg></span></span></a><a class="button button--light button--chromeless is-touchIconBlackPulse u-baseColor--buttonLight button--withIcon button--withSvgIcon u-paddingLeft0"   href="//facebook.com/towardsdatascience" title="Visit “Towards Data Science” on Facebook" aria-label="Visit “Towards Data Science” on Facebook" rel="me" target="_blank"><span class="button-defaultState"><span class="svgIcon svgIcon--facebookFilled svgIcon--25px"><svg class="svgIcon-use" width="25" height="25" viewBox="0 0 25 25" ><path d="M21 12.646C21 7.65 16.97 3.6 12 3.6s-9 4.05-9 9.046a9.026 9.026 0 0 0 7.59 8.924v-6.376H8.395V12.64h2.193v-1.88c0-2.186 1.328-3.375 3.267-3.375.93 0 1.728.07 1.96.1V9.77H14.47c-1.055 0-1.26.503-1.26 1.242v1.63h2.517l-.33 2.554H13.21V21.6c4.398-.597 7.79-4.373 7.79-8.954"/></svg></span></span></a></div></div></div></div><div class="metabar-block u-flex0 u-flexCenter"><div class="u-alignMiddle u-inlineBlock u-verticalAlignTop u-height65 u-xs-height56"><div class="u-alignBlock"><div class="buttonSet buttonSet--wide u-lineHeightInherit"><a class="button button--primary button--light button--chromeless u-accentColor--buttonNormal is-inSiteNavBar u-xs-hide js-signInButton"   href="https://medium.com/m/signin?redirect=https%3A%2F%2Ftowardsdatascience.com%2Fhurricane-harvey-insurtech-case-study-visual-intelligence-is-transforming-claim-response-times-3275042fbd8d&amp;source=--------------------------nav_reg&amp;operation=login" data-action="sign-in-prompt" data-redirect="https://towardsdatascience.com/hurricane-harvey-insurtech-case-study-visual-intelligence-is-transforming-claim-response-times-3275042fbd8d" data-action-source="--------------------------nav_reg">Sign in</a><a class="button button--primary button--light button--withChrome u-accentColor--buttonNormal is-inSiteNavBar js-signUpButton"   href="https://medium.com/m/signin?redirect=https%3A%2F%2Ftowardsdatascience.com%2Fhurricane-harvey-insurtech-case-study-visual-intelligence-is-transforming-claim-response-times-3275042fbd8d&amp;source=--------------------------nav_reg&amp;operation=register" data-action="sign-up-prompt" data-redirect="https://towardsdatascience.com/hurricane-harvey-insurtech-case-study-visual-intelligence-is-transforming-claim-response-times-3275042fbd8d" data-action-source="--------------------------nav_reg">Get started</a></div></div></div></div></div><div class="metabar-inner u-marginAuto u-maxWidth1000 js-metabarBottom"><nav role="navigation" class="metabar-block metabar-block--below u-overflowHidden u-height44"><ul class="u-textAlignLeft u-noWrap u-overflowX u-paddingBottom100 u-sm-paddingLeft20 u-sm-paddingRight20 js-collectionNavItems"><li class="metabar-navItem js-collectionNavItem u-uiTextMedium u-fontSize14 u-inlineBlock u-textUppercase u-letterSpacing003 u-textColorNormal u-xs-paddingRight12 u-xs-marginRight0 u-paddingTop5 u-xs-paddingTop10"><a class="link link--darken u-accentColor--textDarken u-baseColor--link js-homeNav"   href="https://towardsdatascience.com">Home</a></li><li class="metabar-navItem js-collectionNavItem  u-uiTextMedium u-fontSize14 u-inlineBlock u-textUppercase u-letterSpacing003 u-textColorNormal u-xs-paddingRight12 u-xs-marginRight0 u-paddingTop5 u-xs-paddingTop10"><a class="link link--darken u-accentColor--textDarken link--noUnderline u-baseColor--link js-navItemLink"   href="https://towardsdatascience.com/data-science/home">Data Science</a></li><li class="metabar-navItem js-collectionNavItem  u-uiTextMedium u-fontSize14 u-inlineBlock u-textUppercase u-letterSpacing003 u-textColorNormal u-xs-paddingRight12 u-xs-marginRight0 u-paddingTop5 u-xs-paddingTop10"><a class="link link--darken u-accentColor--textDarken link--noUnderline u-baseColor--link js-navItemLink"   href="https://towardsdatascience.com/machine-learning/home">Machine Learning</a></li><li class="metabar-navItem js-collectionNavItem  u-uiTextMedium u-fontSize14 u-inlineBlock u-textUppercase u-letterSpacing003 u-textColorNormal u-xs-paddingRight12 u-xs-marginRight0 u-paddingTop5 u-xs-paddingTop10"><a class="link link--darken u-accentColor--textDarken link--noUnderline u-baseColor--link js-navItemLink"   href="https://towardsdatascience.com/programming/home">Programming</a></li><li class="metabar-navItem js-collectionNavItem  u-uiTextMedium u-fontSize14 u-inlineBlock u-textUppercase u-letterSpacing003 u-textColorNormal u-xs-paddingRight12 u-xs-marginRight0 u-paddingTop5 u-xs-paddingTop10"><a class="link link--darken u-accentColor--textDarken link--noUnderline u-baseColor--link js-navItemLink"   href="https://towardsdatascience.com/data-visualization/home">Visualization</a></li><li class="metabar-navItem js-collectionNavItem  u-uiTextMedium u-fontSize14 u-inlineBlock u-textUppercase u-letterSpacing003 u-textColorNormal u-xs-paddingRight12 u-xs-marginRight0 u-paddingTop5 u-xs-paddingTop10"><a class="link link--darken u-accentColor--textDarken link--noUnderline u-baseColor--link js-navItemLink"   href="https://towardsdatascience.com/newsletters/home">Letters</a></li><li class="metabar-navItem js-collectionNavItem  u-uiTextMedium u-fontSize14 u-inlineBlock u-textUppercase u-letterSpacing003 u-textColorNormal u-xs-paddingRight12 u-xs-marginRight0 u-paddingTop5 u-xs-paddingTop10"><a class="link link--darken u-accentColor--textDarken link--noUnderline u-baseColor--link js-navItemLink"   href="https://towardsdatascience.com/contribute/home">Contribute</a></li><span class="u-borderLeft1 u-paddingLeft12 u-baseColor--borderLight"></span><li class="metabar-navItem js-collectionNavItem  u-paddingLeft0 is-external u-uiTextMedium u-fontSize14 u-inlineBlock u-textUppercase u-letterSpacing003 u-textColorNormal u-xs-paddingRight12 u-xs-marginRight0 u-paddingTop5 u-xs-paddingTop10"><a class="link link--darkenOnHover u-accentColor--textDarken link--noUnderline u-baseColor--link js-navItemLink"   href="https://www.patreon.com/towardsdatascience/" rel="nofollow noopener" target="_blank">Become a Patreon</a></li><li class="metabar-navItem js-collectionNavItem u-uiTextMedium u-fontSize14 u-inlineBlock u-textUppercase u-letterSpacing003 u-textColorNormal u-xs-paddingRight12 u-xs-marginRight0 u-paddingTop5 u-xs-paddingTop10"><a class="button button--chromeless u-baseColor--buttonNormal button--withIcon button--withSvgIcon u-top1"   href="https://towardsdatascience.com/search" title="Search" aria-label="Search"><span class="button-defaultState"><span class="svgIcon svgIcon--search svgIcon--25px"><svg class="svgIcon-use" width="25" height="25"  viewBox="0 0 25 25"><path d="M20.067 18.933l-4.157-4.157a6 6 0 1 0-.884.884l4.157 4.157a.624.624 0 1 0 .884-.884zM6.5 11c0-2.62 2.13-4.75 4.75-4.75S16 8.38 16 11s-2.13 4.75-4.75 4.75S6.5 13.62 6.5 11z"/></svg></span></span></a></li></ul></nav></div></div><div class="metabar metabar--spacer js-metabarSpacer u-tintBgColor  u-height105 u-xs-height95"></div><main role="main"><article class=" u-minHeight100vhOffset65 u-overflowHidden postArticle postArticle--full is-withAccentColors u-marginBottom40"  lang="en"><header class="container u-maxWidth740"><div class="uiScale uiScale-ui--regular uiScale-caption--regular postMetaHeader u-paddingBottom10 row"><div class="col u-size12of12 js-postMetaLockup"><div class="uiScale uiScale-ui--regular uiScale-caption--regular postMetaLockup postMetaLockup--authorWithBio u-flexCenter js-postMetaLockup"><div class="u-flex0"><a class="link u-baseColor--link avatar"   href="https://towardsdatascience.com/@raldon?source=post_header_lockup" data-action="show-user-card" data-action-source="post_header_lockup" data-action-value="44ee44e12515" data-action-type="hover" data-user-id="44ee44e12515" data-collection-slug="towards-data-science" dir="auto"><img  src="https://cdn-images-1.medium.com/fit/c/120/120/1*xyfTiylyHHiLyxJTJQy8AQ.png" class="avatar-image avatar-image--small" alt="Go to the profile of Rafael Aldon"></a></div><div class="u-flex1 u-paddingLeft15 u-overflowHidden"><div class="u-lineHeightTightest"><a class="ds-link ds-link--styleSubtle ui-captionStrong u-inlineBlock link link--darken link--darker"   href="https://towardsdatascience.com/@raldon?source=post_header_lockup" data-action="show-user-card" data-action-source="post_header_lockup" data-action-value="44ee44e12515" data-action-type="hover" data-user-id="44ee44e12515" data-collection-slug="towards-data-science" dir="auto">Rafael Aldon</a><span class="followState js-followState" data-user-id="44ee44e12515"><button class="button button--smallest u-noUserSelect button--withChrome u-baseColor--buttonNormal button--withHover button--unblock js-unblockButton u-marginLeft10 u-xs-hide"  data-action="sign-up-prompt" data-sign-in-action="toggle-block-user" data-requires-token="true" data-redirect="https://towardsdatascience.com/hurricane-harvey-insurtech-case-study-visual-intelligence-is-transforming-claim-response-times-3275042fbd8d" data-action-source="post_header_lockup"><span class="button-label  button-defaultState">Blocked</span><span class="button-label button-hoverState">Unblock</span></button><button class="button button--primary button--smallest u-noUserSelect button--withChrome u-accentColor--buttonNormal button--follow js-followButton u-marginLeft10 u-xs-hide"  data-action="sign-up-prompt" data-sign-in-action="toggle-subscribe-user" data-requires-token="true" data-redirect="https://medium.com/_/subscribe/user/44ee44e12515" data-action-source="post_header_lockup-44ee44e12515-------------------------follow_byline"><span class="button-label  button-defaultState js-buttonLabel">Follow</span><span class="button-label button-activeState">Following</span></button></span></div><div class="ui-caption ui-xs-clamp2 postMetaInline">Early-Stage Venture Capital in Asia | Tech Investor | Startup Advisor | FinTech &amp; Blockchain Enthusiast | Formula 1 Nut</div><div class="ui-caption postMetaInline js-testPostMetaInlineSupplemental"><time datetime="2017-09-20T01:29:31.504Z">Sep 19, 2017</time><span class="middotDivider u-fontSize12"></span><span class="readingTime" title="7 min read"></span></div></div></div></div></div></header><div class="postArticle-content js-postField js-notesSource js-trackedPost"  data-post-id="3275042fbd8d" data-source="post_page" data-collection-id="7f60cf5620c9" data-tracking-context="postPage"><section name="c9db" class="section section--body section--first section--last"><div class="section-divider"><hr class="section-divider"></div><div class="section-content"><div class="section-inner sectionLayout--insetColumn"><h1 name="1f4d" id="1f4d" class="graf graf--h3 graf--leading graf--title">Hurricane Harvey InsurTech Case Study; visual intelligence is transforming claim response times.</h1><figure name="77db" id="77db" class="graf graf--figure graf-after--h3"><div class="aspectRatioPlaceholder is-locked" style="max-width: 700px; max-height: 467px;"><div class="aspectRatioPlaceholder-fill" style="padding-bottom: 66.7%;"></div><img class="graf-image" data-image-id="1*lSrjjYyG8X2ND8hFmjBtAA.png" data-width="940" data-height="627" data-is-featured="true" data-action="zoom" data-action-value="1*lSrjjYyG8X2ND8hFmjBtAA.png" src="https://cdn-images-1.medium.com/max/1600/1*lSrjjYyG8X2ND8hFmjBtAA.png"></div><figcaption class="imageCaption">Hurricane Harvey as seen from the International Space Station</figcaption></figure><p name="70c4" id="70c4" class="graf graf--p graf-after--figure">Storms of unprecedented power have lashed the United States and the Caribbean over the past few weeks, leaving a trail of devastation estimated in the tens of billions of dollars.</p><p name="5e62" id="5e62" class="graf graf--p graf-after--p">The US alone has experienced 212 natural disasters since 1980 with the overall costs totalling $1.2tn, according to the National Oceanic and Atmospheric Association (NOAA).</p><p name="9e5b" id="9e5b" class="graf graf--p graf-after--p">As a venture investor interested in FinTech, I get sight of quite a lot of innovative InsurTech Start-up’s hoping to be the next big thing in insurance. Barely any of these businesses are focused on improving claims management. Why is that?</p><p name="6381" id="6381" class="graf graf--p graf-after--p">Perhaps Claims are considered the least ‘sexy’ aspect of the insurance industry, a necessary evil if you like. Good Insurers understand the claims experience is one of the most important parts of insurance. Insurance, after all, is a promise to make good your losses in case of an accident.</p><p name="0c81" id="0c81" class="graf graf--p graf-after--p">Natural disasters are brutal. They leave people vulnerable and exposed, and a speedy resolution by the insurer is crucial to the customer experience, encourages customer retention and also saves the insurer time and money.</p><p name="dbad" id="dbad" class="graf graf--p graf-after--p">That’s an easy thing to say, but dynamically responding to claims after events of the magnitude of Hurricanes Harvey and Irma is no mean feat. It’s often impossible for people to access the areas for quite some time, by which point storm surges have subsided, and claims can be harder to assess.</p><p name="b164" id="b164" class="graf graf--p graf-after--p">One company actively addressing this challenge for insurers is <a href="https://www.geospatial-insight.com/" data-href="https://www.geospatial-insight.com/" class="markup--anchor markup--p-anchor" rel="noopener" target="_blank">Geospatial Insight</a>. VenturesOne <a href="http://venturesone.com/venturesone-fuels-geospatial-insight/" data-href="http://venturesone.com/venturesone-fuels-geospatial-insight/" class="markup--anchor markup--p-anchor" rel="noopener" target="_blank">announced a growth equity investment in them</a> recently and I was with their team in the UK. They had just delivered incredibly detailed visual intelligence on Hurricane Harvey to enable Insurers and their corporate clients understand the situation at ground level and respond swiftly to claims.</p><p name="669e" id="669e" class="graf graf--p graf-after--p">There are three main challenges that an insurer can address by adopting visual intelligence services after a natural disaster:</p><p name="ad83" id="ad83" class="graf graf--p graf-after--p">1) The approximate total claim size likely as a result of the event.</p><p name="4c60" id="4c60" class="graf graf--p graf-after--p">2) An accurate map of the area impacted by the event to prevent fraudulent claims.</p><p name="3134" id="3134" class="graf graf--p graf-after--p">3) That the proximate cause of the claim is directly related to the event.</p><p name="959f" id="959f" class="graf graf--p graf-after--p">There is a lot of hype around the possibilities of advancing techs like machine learning, big data and drones etc, but I see less in the way of tangible examples of how they can be combined to deliver benefits right now, so here is a real-life example.</p><h3 name="ed9c" id="ed9c" class="graf graf--h3 graf-after--p"><strong class="markup--strong markup--h3-strong">Hurricane Harvey Case Study</strong></h3><p name="c7af" id="c7af" class="graf graf--p graf-after--h3">On August 25th, category 4 Hurricane Harvey makes Landfall near Rockport Texas.</p><figure name="f2d1" id="f2d1" class="graf graf--figure graf-after--p"><div class="aspectRatioPlaceholder is-locked" style="max-width: 700px; max-height: 394px;"><div class="aspectRatioPlaceholder-fill" style="padding-bottom: 56.3%;"></div><img class="graf-image" data-image-id="0*RE_j6FoGu5zb2mXY.png" data-width="815" data-height="459" data-action="zoom" data-action-value="0*RE_j6FoGu5zb2mXY.png" src="https://cdn-images-1.medium.com/max/1600/0*RE_j6FoGu5zb2mXY.png"></div></figure><p name="6e4e" id="6e4e" class="graf graf--p graf-after--figure">Harvey causes catastrophic flooding, with 50+ inches of rainfall in some areas (a record from a tropical cyclone in the USA). Harvey covers over 20,000 square miles in 72 hours, displacing 30,000 people.</p><p name="091e" id="091e" class="graf graf--p graf-after--p"><strong class="markup--strong markup--p-strong">Situational Analysis</strong></p><p name="4dee" id="4dee" class="graf graf--p graf-after--p">The first step was to make an initial assessment of the affected area and a rapid review of expected Insurance customers’ requirements. The densely populated residential and commercial area of greater Houston was set.</p><figure name="3081" id="3081" class="graf graf--figure graf-after--p"><div class="aspectRatioPlaceholder is-locked" style="max-width: 628px; max-height: 353px;"><div class="aspectRatioPlaceholder-fill" style="padding-bottom: 56.2%;"></div><img class="graf-image" data-image-id="0*9zceP3dvu_sbUJsw.png" data-width="628" data-height="353" src="https://cdn-images-1.medium.com/max/1600/0*9zceP3dvu_sbUJsw.png"></div></figure><p name="3f5c" id="3f5c" class="graf graf--p graf-after--figure"><strong class="markup--strong markup--p-strong">Big Data Collection, Processing &amp; Analytics</strong></p><p name="312b" id="312b" class="graf graf--p graf-after--p">Although Harvey made landfall on Friday the weather event continued with torrential rainfall throughout the days that followed. By weds 30th it is estimated that a mind-boggling 24.5 trillion gallons of rainwater was dumped from the Gulf of Mexico across Houston and Southern Texas.</p><figure name="2307" id="2307" class="graf graf--figure graf-after--p"><div class="aspectRatioPlaceholder is-locked" style="max-width: 515px; max-height: 693px;"><div class="aspectRatioPlaceholder-fill" style="padding-bottom: 134.60000000000002%;"></div><img class="graf-image" data-image-id="0*ZDwHwza6N7e4J31e.png" data-width="515" data-height="693" src="https://cdn-images-1.medium.com/max/1600/0*ZDwHwza6N7e4J31e.png"></div></figure><p name="0673" id="0673" class="graf graf--p graf-after--figure">To get the most comprehensive understanding possible a diverse variety of data sets were collated including terrain data, satellite imagery, drone footage from social media scrapes and independent commissioned light aircraft with specialist high-resolution camera imagery.</p><p name="d69b" id="d69b" class="graf graf--p graf-after--p">The team used the data collected from aerial and social to calibrate the threshold used to generate the sentinel footprint. Geospatial Insight then use proprietary algorithms to cluster the areas detected as water into flooded areas</p><figure name="8011" id="8011" class="graf graf--figure graf-after--p"><div class="aspectRatioPlaceholder is-locked" style="max-width: 700px; max-height: 431px;"><div class="aspectRatioPlaceholder-fill" style="padding-bottom: 61.5%;"></div><img class="graf-image" data-image-id="0*cikAKImGstvJtxmH.png" data-width="946" data-height="582" data-action="zoom" data-action-value="0*cikAKImGstvJtxmH.png" src="https://cdn-images-1.medium.com/max/1600/0*cikAKImGstvJtxmH.png"></div></figure><p name="9c18" id="9c18" class="graf graf--p graf-after--figure">To understand the likely impact of Harvey on homes and commercial buildings the multiple data sets were combined to gain insight into flood extents. The colour coded image below shows different data sources.</p><figure name="341d" id="341d" class="graf graf--figure graf-after--p"><div class="aspectRatioPlaceholder is-locked" style="max-width: 700px; max-height: 469px;"><div class="aspectRatioPlaceholder-fill" style="padding-bottom: 67%;"></div><img class="graf-image" data-image-id="0*lVYEn3LbTs4tsPT8.png" data-width="908" data-height="608" data-action="zoom" data-action-value="0*lVYEn3LbTs4tsPT8.png" src="https://cdn-images-1.medium.com/max/1600/0*lVYEn3LbTs4tsPT8.png"></div></figure><p name="e293" id="e293" class="graf graf--p graf-after--figure">The blue is derived from the National Oceanic and Atmosphere Association (NOAA) imagery and an aerial survey using a Midas oblique camera system.</p><p name="8c27" id="8c27" class="graf graf--p graf-after--p">The red is Sentinel 1 RADAR satellite that can penetrate cloud cover to identify areas of standing water.</p><p name="beaa" id="beaa" class="graf graf--p graf-after--p">The small pockets of yellow are derived from Geospatial Insight’s social media scraping tool to find photos and videos of the event which can then be mapped to build the extents from video evidence. Typically, the team use their global network of licensed UAV operators that work to agreed SLA’s to map flood areas with drones, however, drones were banned over Houston during this time frame due to emergency services using the airspace for rescues etc.</p><p name="f47d" id="f47d" class="graf graf--p graf-after--p">Footage like the example below were identified and then the flight path and flood extents expertly mapped.</p><figure name="502e" id="502e" class="graf graf--figure graf--iframe graf-after--p"><div class="aspectRatioPlaceholder is-locked"><div class="aspectRatioPlaceholder-fill" style="padding-bottom: 56.2%;"></div><div class="iframeContainer"><IFRAME data-width="854" data-height="480" width="700" height="393" src="/media/b644432f2314eb1fb10f041164f8c996?postId=3275042fbd8d" data-media-id="b644432f2314eb1fb10f041164f8c996" data-thumbnail="https://i.embed.ly/1/image?url=https%3A%2F%2Fi.ytimg.com%2Fvi%2FbjQS5q2l41Q%2Fhqdefault.jpg&amp;key=a19fcc184b9711e1b4764040d3dc5c07" allowfullscreen frameborder="0"></IFRAME></div></div></figure><p name="62fa" id="62fa" class="graf graf--p graf-after--figure"><strong class="markup--strong markup--p-strong">Why was the flooding so severe?</strong></p><p name="5641" id="5641" class="graf graf--p graf-after--p">You can clearly see the two large blue reservoirs on the west side of Houston, Addicks to the North of Interstate 10, and Barker to the South. They are designed to protect Houston from flooding and both dams feed into the Buffalo Bayou. The reservoirs are surrounded by parks and residential areas and by Monday evening water levels had already reached record levels, measuring 105 feet at Addicks (North) and 99 feet at Barker (South).</p><figure name="c1a9" id="c1a9" class="graf graf--figure graf-after--p"><div class="aspectRatioPlaceholder is-locked" style="max-width: 684px; max-height: 560px;"><div class="aspectRatioPlaceholder-fill" style="padding-bottom: 81.89999999999999%;"></div><img class="graf-image" data-image-id="0*8CbPxaZpkrghMTG0.png" data-width="684" data-height="560" src="https://cdn-images-1.medium.com/max/1600/0*8CbPxaZpkrghMTG0.png"></div></figure><p name="09a5" id="09a5" class="graf graf--p graf-after--figure">Local officials hoped to prevent a spill-over by slowly releasing water from both the Addicks and Barker dams on Tues and Weds. However, the storm surge was so great that the engineers had to release water through the dam gates much earlier than expected or risk it spilling over and causing further damage to homes. A warning was given to homes to evacuate in the early hours of Monday morning, however, the decision was made to release the pressure late Sunday night and many residents became stranded in the resulting swell.</p><figure name="a314" id="a314" class="graf graf--figure graf-after--p"><div class="aspectRatioPlaceholder is-locked" style="max-width: 425px; max-height: 395px;"><div class="aspectRatioPlaceholder-fill" style="padding-bottom: 92.9%;"></div><img class="graf-image" data-image-id="0*4Hh1k_jjaZo7DMLA.png" data-width="425" data-height="395" src="https://cdn-images-1.medium.com/max/1600/0*4Hh1k_jjaZo7DMLA.png"></div></figure><p name="c4fd" id="c4fd" class="graf graf--p graf-after--figure"><strong class="markup--strong markup--p-strong">Accelerating Claims with Visual Intelligence</strong></p><p name="e2df" id="e2df" class="graf graf--p graf-after--p">In order to provide the intelligence required to rapidly address insurance claims, the Geospatial Insight team needed to first make sense of huge amounts of unstructured data.</p><p name="c4de" id="c4de" class="graf graf--p graf-after--p">Not only the diverse image sources but also client information for insurance customers and corporate responsibility data like home addresses of employees to map the affected customers and staff.</p><p name="2994" id="2994" class="graf graf--p graf-after--p">This data was quickly mapped and the multiple image sources applied as layers to allow corporate clients to access and make sense of the information via Geospatial Insights dedicated customer portal.</p><figure name="5068" id="5068" class="graf graf--figure graf-after--p"><div class="aspectRatioPlaceholder is-locked" style="max-width: 700px; max-height: 327px;"><div class="aspectRatioPlaceholder-fill" style="padding-bottom: 46.6%;"></div><img class="graf-image" data-image-id="0*5fjLzerjd7MQ9nsD.png" data-width="939" data-height="438" data-action="zoom" data-action-value="0*5fjLzerjd7MQ9nsD.png" src="https://cdn-images-1.medium.com/max/1600/0*5fjLzerjd7MQ9nsD.png"></div></figure><p name="2213" id="2213" class="graf graf--p graf-after--figure">The image above shows the client portal with claim location points identified in yellow.</p><p name="fb07" id="fb07" class="graf graf--p graf-after--p">High-resolution satellite images can be a good indicator however they are top-down view so much harder to get an accurate perspective on the level of damage on a property. Images at an oblique angle were needed to help quantify this over a vast area and thus Geospatial Insight commissioned a light aircraft equipped with a Midas 5 camera to map the most affected region for high-resolution imagery.</p><p name="a34e" id="a34e" class="graf graf--p graf-after--p">The visualisation below shows how this camera is able to capture oblique angles in four directions simultaneously (along with an overhead view).</p><figure name="7608" id="7608" class="graf graf--figure graf-after--p"><div class="aspectRatioPlaceholder is-locked" style="max-width: 609px; max-height: 941px;"><div class="aspectRatioPlaceholder-fill" style="padding-bottom: 154.5%;"></div><img class="graf-image" data-image-id="0*Uzhvf31E3eFECgQW.png" data-width="609" data-height="941" src="https://cdn-images-1.medium.com/max/1600/0*Uzhvf31E3eFECgQW.png"></div></figure><p name="a90e" id="a90e" class="graf graf--p graf-after--figure">Using this technique, huge areas could be imaged in high resolution and then mapped to provide oblique angled images in North, South, East and West orientations for accurate analysis of identified claim locations.</p><figure name="58ae" id="58ae" class="graf graf--figure graf-after--p"><div class="aspectRatioPlaceholder is-locked" style="max-width: 700px; max-height: 476px;"><div class="aspectRatioPlaceholder-fill" style="padding-bottom: 68%;"></div><img class="graf-image" data-image-id="0*q3zSh_dGS5fxievW.png" data-width="778" data-height="529" data-action="zoom" data-action-value="0*q3zSh_dGS5fxievW.png" src="https://cdn-images-1.medium.com/max/1600/0*q3zSh_dGS5fxievW.png"></div></figure><p name="fd83" id="fd83" class="graf graf--p graf-after--figure">With this resolution and volume of data, the Geospatial Insight team could identify the evidence of flooding such as remaining water, sediment and waste outside houses even after the flooding has drained away. Below is an example image showing home furnishings being disposed of. You can clearly see the raised swimming pools that remained clean and blue compared to those that were ruined by the storm surge.</p><figure name="4e9f" id="4e9f" class="graf graf--figure graf-after--p"><div class="aspectRatioPlaceholder is-locked" style="max-width: 700px; max-height: 469px;"><div class="aspectRatioPlaceholder-fill" style="padding-bottom: 67%;"></div><img class="graf-image" data-image-id="0*LSgSGuCXfYw57847.png" data-width="815" data-height="546" data-action="zoom" data-action-value="0*LSgSGuCXfYw57847.png" src="https://cdn-images-1.medium.com/max/1600/0*LSgSGuCXfYw57847.png"></div></figure><p name="1d17" id="1d17" class="graf graf--p graf-after--figure"><strong class="markup--strong markup--p-strong">Rebuilding Lives After Disaster</strong></p><p name="bf62" id="bf62" class="graf graf--p graf-after--p">Sadly, it seems many residents of Houston were uninsured and face rebuilding their lives without any form of insurance pay-out. For those with cover, getting access to funds quickly will make all the difference.</p><p name="71a4" id="71a4" class="graf graf--p graf-after--p">By embracing the kind of technology deployed above, insurers can make a meaningful difference in helping residents, businesses and communities get back on their feet as quickly as possible.</p><p name="7d13" id="7d13" class="graf graf--p graf-after--p">— — — — — — — —</p><p name="0549" id="0549" class="graf graf--p graf-after--p graf--trailing">For more info on the company you can visit <a href="http://www.geospatial-insight.com/" data-href="http://www.geospatial-insight.com/" class="markup--anchor markup--p-anchor" rel="nofollow noopener noopener" target="_blank">www.geospatial-insight.com</a> or just message me and I would be happy to afford you an introduction to the team.</p></div></div></section></div><footer class="u-paddingTop10"><div class="container u-maxWidth740"><div class="row"><div class="col u-size12of12"></div></div><div class="row"><div class="col u-size12of12 js-postTags"><div class="u-paddingBottom10"><ul class="tags tags--postTags tags--borderless"><li><a class="link u-baseColor--link"   href="https://towardsdatascience.com/tagged/hurricane-harvey?source=post" data-action-source="post" data-collection-slug="towards-data-science">Hurricane Harvey</a></li><li><a class="link u-baseColor--link"   href="https://towardsdatascience.com/tagged/insurance?source=post" data-action-source="post" data-collection-slug="towards-data-science">Insurance</a></li><li><a class="link u-baseColor--link"   href="https://towardsdatascience.com/tagged/machine-learning?source=post" data-action-source="post" data-collection-slug="towards-data-science">Machine Learning</a></li><li><a class="link u-baseColor--link"   href="https://towardsdatascience.com/tagged/big-data?source=post" data-action-source="post" data-collection-slug="towards-data-science">Big Data</a></li><li><a class="link u-baseColor--link"   href="https://towardsdatascience.com/tagged/towards-data-science?source=post" data-action-source="post" data-collection-slug="towards-data-science">Towards Data Science</a></li></ul></div></div></div><section class="uiScale uiScale-ui--small uiScale-caption--regular u-borderTopLightest u-marginTop10 u-paddingTop20"><div class="ui-h3 u-textColorDarker u-fontSize22">One clap, two clap, three clap, forty?</div><p class="ui-body u-marginBottom20 u-textColorDark u-fontSize16">By clapping more or less, you can signal to us which stories really stand out.</p></section><div class="postActions js-postActionsFooter"><div class="u-flexCenter"><div class="u-flex1"><div class="multirecommend js-actionMultirecommend u-flexCenter u-width60" data-post-id="3275042fbd8d" data-is-icon-29px="true" data-is-circle="true" data-has-recommend-list="true" data-source="post_actions_footer-----3275042fbd8d---------------------clap_footer"><div class="u-relative u-foreground"><button class="button button--large button--circle button--withChrome u-baseColor--buttonNormal button--withIcon button--withSvgIcon clapButton js-actionMultirecommendButton clapButton--largePill u-relative u-foreground u-xs-paddingLeft13 u-width60 u-height60 u-accentColor--textNormal u-accentColor--buttonNormal clap-onboardingcollection"  data-action="sign-up-prompt" data-sign-in-action="multivote" data-requires-token="true" data-redirect="https://medium.com/_/vote/p/3275042fbd8d" data-action-source="post_actions_footer-----3275042fbd8d---------------------clap_footer" aria-label="Clap"><span class="button-defaultState"><span class="svgIcon svgIcon--clap svgIcon--33px u-relative u-topNegative2 u-xs-top0"><svg class="svgIcon-use" width="33" height="33" viewBox="0 0 33 33" ><path d="M28.86 17.342l-3.64-6.402c-.292-.433-.712-.729-1.163-.8a1.124 1.124 0 0 0-.889.213c-.63.488-.742 1.181-.33 2.061l1.222 2.587 1.4 2.46c2.234 4.085 1.511 8.007-2.145 11.663-.26.26-.526.49-.797.707 1.42-.084 2.881-.683 4.292-2.094 3.822-3.823 3.565-7.876 2.05-10.395zm-6.252 11.075c3.352-3.35 3.998-6.775 1.978-10.469l-3.378-5.945c-.292-.432-.712-.728-1.163-.8a1.122 1.122 0 0 0-.89.213c-.63.49-.742 1.182-.33 2.061l1.72 3.638a.502.502 0 0 1-.806.568l-8.91-8.91a1.335 1.335 0 0 0-1.887 1.886l5.292 5.292a.5.5 0 0 1-.707.707l-5.292-5.292-1.492-1.492c-.503-.503-1.382-.505-1.887 0a1.337 1.337 0 0 0 0 1.886l1.493 1.492 5.292 5.292a.499.499 0 0 1-.353.854.5.5 0 0 1-.354-.147L5.642 13.96a1.338 1.338 0 0 0-1.887 0 1.338 1.338 0 0 0 0 1.887l2.23 2.228 3.322 3.324a.499.499 0 0 1-.353.853.502.502 0 0 1-.354-.146l-3.323-3.324a1.333 1.333 0 0 0-1.886 0 1.325 1.325 0 0 0-.39.943c0 .356.138.691.39.943l6.396 6.397c3.528 3.53 8.86 5.313 12.821 1.353zM12.73 9.26l5.68 5.68-.49-1.037c-.518-1.107-.426-2.13.224-2.89l-3.303-3.304a1.337 1.337 0 0 0-1.886 0 1.326 1.326 0 0 0-.39.944c0 .217.067.42.165.607zm14.787 19.184c-1.599 1.6-3.417 2.392-5.353 2.392-.349 0-.7-.03-1.058-.082a7.922 7.922 0 0 1-3.667.887c-3.049 0-6.115-1.626-8.359-3.87l-6.396-6.397A2.315 2.315 0 0 1 2 19.724a2.327 2.327 0 0 1 1.923-2.296l-.875-.875a2.339 2.339 0 0 1 0-3.3 2.33 2.33 0 0 1 1.24-.647l-.139-.139c-.91-.91-.91-2.39 0-3.3.884-.884 2.421-.882 3.301 0l.138.14a2.335 2.335 0 0 1 3.948-1.24l.093.092c.091-.423.291-.828.62-1.157a2.336 2.336 0 0 1 3.3 0l3.384 3.386a2.167 2.167 0 0 1 1.271-.173c.534.086 1.03.354 1.441.765.11-.549.415-1.034.911-1.418a2.12 2.12 0 0 1 1.661-.41c.727.117 1.385.565 1.853 1.262l3.652 6.423c1.704 2.832 2.025 7.377-2.205 11.607zM13.217.484l-1.917.882 2.37 2.837-.454-3.719zm8.487.877l-1.928-.86-.44 3.697 2.368-2.837zM16.5 3.293L15.478-.005h2.044L16.5 3.293z" fill-rule="evenodd"/></svg></span></span><span class="button-activeState"><span class="svgIcon svgIcon--clapFilled svgIcon--33px u-relative u-topNegative2 u-xs-top0"><svg class="svgIcon-use" width="33" height="33" viewBox="0 0 33 33" ><g fill-rule="evenodd"><path d="M29.58 17.1l-3.854-6.78c-.365-.543-.876-.899-1.431-.989a1.491 1.491 0 0 0-1.16.281c-.42.327-.65.736-.7 1.207v.001l3.623 6.367c2.46 4.498 1.67 8.802-2.333 12.807-.265.265-.536.505-.81.728 1.973-.222 3.474-1.286 4.45-2.263 4.166-4.165 3.875-8.6 2.215-11.36zm-4.831.82l-3.581-6.3c-.296-.439-.725-.742-1.183-.815a1.105 1.105 0 0 0-.89.213c-.647.502-.755 1.188-.33 2.098l1.825 3.858a.601.601 0 0 1-.197.747.596.596 0 0 1-.77-.067L10.178 8.21c-.508-.506-1.393-.506-1.901 0a1.335 1.335 0 0 0-.393.95c0 .36.139.698.393.95v.001l5.61 5.61a.599.599 0 1 1-.848.847l-5.606-5.606c-.001 0-.002 0-.003-.002L5.848 9.375a1.349 1.349 0 0 0-1.902 0 1.348 1.348 0 0 0 0 1.901l1.582 1.582 5.61 5.61a.6.6 0 0 1-.848.848l-5.61-5.61c-.51-.508-1.393-.508-1.9 0a1.332 1.332 0 0 0-.394.95c0 .36.139.697.393.952l2.363 2.362c.002.001.002.002.002.003l3.52 3.52a.6.6 0 0 1-.848.847l-3.522-3.523h-.001a1.336 1.336 0 0 0-.95-.393 1.345 1.345 0 0 0-.949 2.295l6.779 6.78c3.715 3.713 9.327 5.598 13.49 1.434 3.527-3.528 4.21-7.13 2.086-11.015zM11.817 7.727c.06-.328.213-.64.466-.893.64-.64 1.755-.64 2.396 0l3.232 3.232c-.82.783-1.09 1.833-.764 2.992l-5.33-5.33z"/><path d="M13.285.48l-1.916.881 2.37 2.837z"/><path d="M21.719 1.361L19.79.501l-.44 3.697z"/><path d="M16.502 3.298L15.481 0h2.043z"/></g></svg></span></span></button><div class="clapUndo u-width60 u-round u-height32 u-absolute u-borderBox u-paddingRight5 u-transition--transform200Spring u-background--brandSageLighter js-clapUndo" style="top: 14px; padding: 2px;"><button class="button button--chromeless u-baseColor--buttonNormal button--withIcon button--withSvgIcon u-floatRight"  data-action="multivote-undo" data-action-value="3275042fbd8d"><span class="svgIcon svgIcon--removeThin svgIcon--29px"><svg class="svgIcon-use" width="29" height="29" viewBox="0 0 29 29" ><path d="M20.13 8.11l-5.61 5.61-5.609-5.61-.801.801 5.61 5.61-5.61 5.61.801.8 5.61-5.609 5.61 5.61.8-.801-5.609-5.61 5.61-5.61" fill-rule="evenodd"/></svg></span></button></div></div><span class="u-textAlignCenter u-relative u-background js-actionMultirecommendCount u-marginLeft10"><button class="button button--chromeless u-baseColor--buttonNormal js-multirecommendCountButton"  data-action="show-recommends" data-action-value="3275042fbd8d">30</button></span></div></div><div class="buttonSet u-flex0"><button class="button button--large button--dark button--chromeless is-touchIconBlackPulse u-baseColor--buttonDark button--withIcon button--withSvgIcon"  data-action="scroll-to-responses" data-action-source="post_actions_footer"><span class="svgIcon svgIcon--response svgIcon--29px"><svg class="svgIcon-use" width="29" height="29" viewBox="0 0 29 29" ><path d="M21.27 20.058c1.89-1.826 2.754-4.17 2.754-6.674C24.024 8.21 19.67 4 14.1 4 8.53 4 4 8.21 4 13.384c0 5.175 4.53 9.385 10.1 9.385 1.007 0 2-.14 2.95-.41.285.25.592.49.918.7 1.306.87 2.716 1.31 4.19 1.31.276-.01.494-.14.6-.36a.625.625 0 0 0-.052-.65c-.61-.84-1.042-1.71-1.282-2.58a5.417 5.417 0 0 1-.154-.75zm-3.85 1.324l-.083-.28-.388.12a9.72 9.72 0 0 1-2.85.424c-4.96 0-8.99-3.706-8.99-8.262 0-4.556 4.03-8.263 8.99-8.263 4.95 0 8.77 3.71 8.77 8.27 0 2.25-.75 4.35-2.5 5.92l-.24.21v.32c0 .07 0 .19.02.37.03.29.1.6.19.92.19.7.49 1.4.89 2.08-.93-.14-1.83-.49-2.67-1.06-.34-.22-.88-.48-1.16-.74z"/></svg></span></button><button class="button button--large button--dark button--chromeless is-touchIconBlackPulse u-baseColor--buttonDark button--withIcon button--withSvgIcon u-xs-hide"  title="Share on Twitter" aria-label="Share on Twitter" data-action="share-on-twitter" data-action-source="post_actions_footer"><span class="svgIcon svgIcon--twitter svgIcon--29px"><svg class="svgIcon-use" width="29" height="29" viewBox="0 0 29 29" ><path d="M21.967 11.8c.018 5.93-4.607 11.18-11.177 11.18-2.172 0-4.25-.62-6.047-1.76l-.268.422-.038.5.186.013.168.012c.3.02.44.032.6.046 2.06-.026 3.95-.686 5.49-1.86l1.12-.85-1.4-.048c-1.57-.055-2.92-1.08-3.36-2.51l-.48.146-.05.5c.22.03.48.05.75.08.48-.02.87-.07 1.25-.15l2.33-.49-2.32-.49c-1.68-.35-2.91-1.83-2.91-3.55 0-.05 0-.01-.01.03l-.49-.1-.25.44c.63.36 1.35.57 2.07.58l1.7.04L7.4 13c-.978-.662-1.59-1.79-1.618-3.047a4.08 4.08 0 0 1 .524-1.8l-.825.07a12.188 12.188 0 0 0 8.81 4.515l.59.033-.06-.59v-.02c-.05-.43-.06-.63-.06-.87a3.617 3.617 0 0 1 6.27-2.45l.2.21.28-.06c1.01-.22 1.94-.59 2.73-1.09l-.75-.56c-.1.36-.04.89.12 1.36.23.68.58 1.13 1.17.85l-.21-.45-.42-.27c-.52.8-1.17 1.48-1.92 2L22 11l.016.28c.013.2.014.35 0 .52v.04zm.998.038c.018-.22.017-.417 0-.66l-.498.034.284.41a8.183 8.183 0 0 0 2.2-2.267l.97-1.48-1.6.755c.17-.08.3-.02.34.03a.914.914 0 0 1-.13-.292c-.1-.297-.13-.64-.1-.766l.36-1.254-1.1.695c-.69.438-1.51.764-2.41.963l.48.15a4.574 4.574 0 0 0-3.38-1.484 4.616 4.616 0 0 0-4.61 4.613c0 .29.02.51.08.984l.01.02.5-.06.03-.5c-3.17-.18-6.1-1.7-8.08-4.15l-.48-.56-.36.64c-.39.69-.62 1.48-.65 2.28.04 1.61.81 3.04 2.06 3.88l.3-.92c-.55-.02-1.11-.17-1.6-.45l-.59-.34-.14.67c-.02.08-.02.16 0 .24-.01 2.12 1.55 4.01 3.69 4.46l.1-.49-.1-.49c-.33.07-.67.12-1.03.14-.18-.02-.43-.05-.64-.07l-.76-.09.23.73c.57 1.84 2.29 3.14 4.28 3.21l-.28-.89a8.252 8.252 0 0 1-4.85 1.66c-.12-.01-.26-.02-.56-.05l-.17-.01-.18-.01L2.53 21l1.694 1.07a12.233 12.233 0 0 0 6.58 1.917c7.156 0 12.2-5.73 12.18-12.18l-.002.04z"/></svg></span></button><button class="button button--large button--dark button--chromeless is-touchIconBlackPulse u-baseColor--buttonDark button--withIcon button--withSvgIcon u-xs-hide"  title="Share on Facebook" aria-label="Share on Facebook" data-action="share-on-facebook" data-action-source="post_actions_footer"><span class="svgIcon svgIcon--facebook svgIcon--29px"><svg class="svgIcon-use" width="29" height="29" viewBox="0 0 29 29" ><path d="M16.39 23.61v-5.808h1.846a.55.55 0 0 0 .546-.48l.36-2.797a.551.551 0 0 0-.547-.62H16.39V12.67c0-.67.12-.813.828-.813h1.474a.55.55 0 0 0 .55-.55V8.803a.55.55 0 0 0-.477-.545c-.436-.06-1.36-.116-2.22-.116-2.5 0-4.13 1.62-4.13 4.248v1.513H10.56a.551.551 0 0 0-.55.55v2.797c0 .304.248.55.55.55h1.855v5.76c-4.172-.96-7.215-4.7-7.215-9.1 0-5.17 4.17-9.36 9.31-9.36 5.14 0 9.31 4.19 9.31 9.36 0 4.48-3.155 8.27-7.43 9.15M14.51 4C8.76 4 4.1 8.684 4.1 14.46c0 5.162 3.75 9.523 8.778 10.32a.55.55 0 0 0 .637-.543v-6.985a.551.551 0 0 0-.55-.55H11.11v-1.697h1.855a.55.55 0 0 0 .55-.55v-2.063c0-2.02 1.136-3.148 3.03-3.148.567 0 1.156.027 1.597.06v1.453h-.924c-1.363 0-1.93.675-1.93 1.912v1.78c0 .3.247.55.55.55h2.132l-.218 1.69H15.84c-.305 0-.55.24-.55.55v7.02c0 .33.293.59.623.54 5.135-.7 9.007-5.11 9.007-10.36C24.92 8.68 20.26 4 14.51 4"/></svg></span></button><button class="button button--large button--dark button--chromeless u-baseColor--buttonDark button--withIcon button--withSvgIcon u-xs-show"  title="Share this story on Twitter or Facebook" aria-label="Share this story on Twitter or Facebook" data-action="show-share-popover" data-action-source="post_actions_footer"><span class="svgIcon svgIcon--share svgIcon--29px"><svg class="svgIcon-use" width="29" height="29" viewBox="0 0 29 29" ><path d="M20.385 8H19a.5.5 0 1 0 .011 1h1.39c.43 0 .84.168 1.14.473.31.305.48.71.48 1.142v10.77c0 .43-.17.837-.47 1.142-.3.305-.71.473-1.14.473H8.62c-.43 0-.84-.168-1.144-.473a1.603 1.603 0 0 1-.473-1.142v-10.77c0-.43.17-.837.48-1.142A1.599 1.599 0 0 1 8.62 9H10a.502.502 0 0 0 0-1H8.615c-.67 0-1.338.255-1.85.766-.51.51-.765 1.18-.765 1.85v10.77c0 .668.255 1.337.766 1.848.51.51 1.18.766 1.85.766h11.77c.668 0 1.337-.255 1.848-.766.51-.51.766-1.18.766-1.85v-10.77c0-.668-.255-1.337-.766-1.848A2.61 2.61 0 0 0 20.384 8zm-8.67-2.508L14 3.207v8.362c0 .27.224.5.5.5s.5-.23.5-.5V3.2l2.285 2.285a.49.49 0 0 0 .704-.001.511.511 0 0 0 0-.708l-3.14-3.14a.504.504 0 0 0-.71 0L11 4.776a.501.501 0 0 0 .71.706" fill-rule="evenodd"/></svg></span></button></div></div></div></div><div class="u-maxWidth740 u-paddingTop20 u-marginTop20 u-borderTopLightest container u-paddingBottom20 u-xs-paddingBottom10 js-postAttributionFooterContainer"><div class="row js-postFooterInfo"><div class="col u-size6of12 u-xs-size12of12"><li class="uiScale uiScale-ui--small uiScale-caption--regular u-block u-paddingBottom18 js-cardUser"><div class="u-marginLeft20 u-floatRight"><span class="followState js-followState" data-user-id="44ee44e12515"><button class="button button--small u-noUserSelect button--withChrome u-baseColor--buttonNormal button--withHover button--unblock js-unblockButton"  data-action="sign-up-prompt" data-sign-in-action="toggle-block-user" data-requires-token="true" data-redirect="https://towardsdatascience.com/hurricane-harvey-insurtech-case-study-visual-intelligence-is-transforming-claim-response-times-3275042fbd8d" data-action-source="footer_card"><span class="button-label  button-defaultState">Blocked</span><span class="button-label button-hoverState">Unblock</span></button><button class="button button--primary button--small u-noUserSelect button--withChrome u-accentColor--buttonNormal button--follow js-followButton"  data-action="sign-up-prompt" data-sign-in-action="toggle-subscribe-user" data-requires-token="true" data-redirect="https://medium.com/_/subscribe/user/44ee44e12515" data-action-source="footer_card-44ee44e12515-------------------------follow_footer"><span class="button-label  button-defaultState js-buttonLabel">Follow</span><span class="button-label button-activeState">Following</span></button></span></div><div class="u-tableCell"><a class="link u-baseColor--link avatar"   href="https://towardsdatascience.com/@raldon?source=footer_card" title="Go to the profile of Rafael Aldon" aria-label="Go to the profile of Rafael Aldon" data-action-source="footer_card" data-user-id="44ee44e12515" data-collection-slug="towards-data-science" dir="auto"><img  src="https://cdn-images-1.medium.com/fit/c/120/120/1*xyfTiylyHHiLyxJTJQy8AQ.png" class="avatar-image avatar-image--small" alt="Go to the profile of Rafael Aldon"></a></div><div class="u-tableCell u-verticalAlignMiddle u-breakWord u-paddingLeft15"><h3 class="ui-h3 u-fontSize18 u-lineHeightTighter u-marginBottom4"><a class="link link--primary u-accentColor--hoverTextNormal"   href="https://towardsdatascience.com/@raldon" property="cc:attributionName" title="Go to the profile of Rafael Aldon" aria-label="Go to the profile of Rafael Aldon" rel="author cc:attributionUrl" data-user-id="44ee44e12515" data-collection-slug="towards-data-science" dir="auto">Rafael Aldon</a></h3><p class="ui-body u-fontSize14 u-lineHeightBaseSans u-textColorDark u-marginBottom4">Early-Stage Venture Capital in Asia | Tech Investor | Startup Advisor | FinTech &amp; Blockchain Enthusiast | Formula 1 Nut</p></div></li></div><div class="col u-size6of12 u-xs-size12of12 u-xs-marginTop30"><li class="uiScale uiScale-ui--small uiScale-caption--regular u-block u-paddingBottom18 js-cardCollection"><div class="u-marginLeft20 u-floatRight"><button class="button button--primary button--small u-noUserSelect button--withChrome u-accentColor--buttonNormal js-relationshipButton"  data-action="sign-up-prompt" data-sign-in-action="toggle-follow-collection" data-requires-token="true" data-redirect="https://medium.com/_/subscribe/collection/towards-data-science" data-action-source="----7f60cf5620c9----------------------follow_footer" data-collection-id="7f60cf5620c9"><span class="button-label  js-buttonLabel">Follow</span></button></div><div class="u-tableCell "><a class="link u-baseColor--link avatar avatar--roundedRectangle"   href="https://towardsdatascience.com?source=footer_card" title="Go to Towards Data Science" aria-label="Go to Towards Data Science" data-action-source="footer_card" data-collection-slug="towards-data-science"><img src="https://cdn-images-1.medium.com/fit/c/120/120/1*F0LADxTtsKOgmPa-_7iUEQ.jpeg" class="avatar-image u-size60x60" alt="Towards Data Science"></a></div><div class="u-tableCell u-verticalAlignMiddle u-breakWord u-paddingLeft15"><h3 class="ui-h3 u-fontSize18 u-lineHeightTighter u-marginBottom4"><a class="link link--primary u-accentColor--hoverTextNormal"   href="https://towardsdatascience.com?source=footer_card" rel="collection" data-action-source="footer_card" data-collection-slug="towards-data-science">Towards Data Science</a></h3><p class="ui-body u-fontSize14 u-lineHeightBaseSans u-textColorDark u-marginBottom4">Sharing concepts, ideas, and codes.</p><div class="buttonSet"></div></div></li></div></div></div><div class="js-postFooterPlacements"></div><div class="u-padding0 u-clearfix u-backgroundGrayLightest u-print-hide supplementalPostContent js-responsesWrapper"></div><div class="supplementalPostContent js-heroPromo"></div></footer></article></main><div class="u-marginAuto u-maxWidth1000"><div class="js-postShareWidget u-foreground u-sm-hide u-transition--fadeOut300 u-fixed"><ul><li class="u-textAlignCenter u-marginVertical10"><div class="multirecommend js-actionMultirecommend u-flexColumn u-marginBottom10 u-width60" data-post-id="3275042fbd8d" data-is-icon-29px="true" data-is-vertical="true" data-is-circle="true" data-has-recommend-list="true" data-source="post_share_widget-----3275042fbd8d---------------------clap_sidebar"><div class="u-relative u-foreground"><button class="button button--large button--circle button--withChrome u-baseColor--buttonNormal button--withIcon button--withSvgIcon clapButton js-actionMultirecommendButton clapButton--largePill u-relative u-foreground u-xs-paddingLeft13 u-width60 u-height60 u-accentColor--textNormal u-accentColor--buttonNormal"  data-action="sign-up-prompt" data-sign-in-action="multivote" data-requires-token="true" data-redirect="https://medium.com/_/vote/p/3275042fbd8d" data-action-source="post_share_widget-----3275042fbd8d---------------------clap_sidebar" aria-label="Clap"><span class="button-defaultState"><span class="svgIcon svgIcon--clap svgIcon--33px u-relative u-topNegative2 u-xs-top0"><svg class="svgIcon-use" width="33" height="33" viewBox="0 0 33 33" ><path d="M28.86 17.342l-3.64-6.402c-.292-.433-.712-.729-1.163-.8a1.124 1.124 0 0 0-.889.213c-.63.488-.742 1.181-.33 2.061l1.222 2.587 1.4 2.46c2.234 4.085 1.511 8.007-2.145 11.663-.26.26-.526.49-.797.707 1.42-.084 2.881-.683 4.292-2.094 3.822-3.823 3.565-7.876 2.05-10.395zm-6.252 11.075c3.352-3.35 3.998-6.775 1.978-10.469l-3.378-5.945c-.292-.432-.712-.728-1.163-.8a1.122 1.122 0 0 0-.89.213c-.63.49-.742 1.182-.33 2.061l1.72 3.638a.502.502 0 0 1-.806.568l-8.91-8.91a1.335 1.335 0 0 0-1.887 1.886l5.292 5.292a.5.5 0 0 1-.707.707l-5.292-5.292-1.492-1.492c-.503-.503-1.382-.505-1.887 0a1.337 1.337 0 0 0 0 1.886l1.493 1.492 5.292 5.292a.499.499 0 0 1-.353.854.5.5 0 0 1-.354-.147L5.642 13.96a1.338 1.338 0 0 0-1.887 0 1.338 1.338 0 0 0 0 1.887l2.23 2.228 3.322 3.324a.499.499 0 0 1-.353.853.502.502 0 0 1-.354-.146l-3.323-3.324a1.333 1.333 0 0 0-1.886 0 1.325 1.325 0 0 0-.39.943c0 .356.138.691.39.943l6.396 6.397c3.528 3.53 8.86 5.313 12.821 1.353zM12.73 9.26l5.68 5.68-.49-1.037c-.518-1.107-.426-2.13.224-2.89l-3.303-3.304a1.337 1.337 0 0 0-1.886 0 1.326 1.326 0 0 0-.39.944c0 .217.067.42.165.607zm14.787 19.184c-1.599 1.6-3.417 2.392-5.353 2.392-.349 0-.7-.03-1.058-.082a7.922 7.922 0 0 1-3.667.887c-3.049 0-6.115-1.626-8.359-3.87l-6.396-6.397A2.315 2.315 0 0 1 2 19.724a2.327 2.327 0 0 1 1.923-2.296l-.875-.875a2.339 2.339 0 0 1 0-3.3 2.33 2.33 0 0 1 1.24-.647l-.139-.139c-.91-.91-.91-2.39 0-3.3.884-.884 2.421-.882 3.301 0l.138.14a2.335 2.335 0 0 1 3.948-1.24l.093.092c.091-.423.291-.828.62-1.157a2.336 2.336 0 0 1 3.3 0l3.384 3.386a2.167 2.167 0 0 1 1.271-.173c.534.086 1.03.354 1.441.765.11-.549.415-1.034.911-1.418a2.12 2.12 0 0 1 1.661-.41c.727.117 1.385.565 1.853 1.262l3.652 6.423c1.704 2.832 2.025 7.377-2.205 11.607zM13.217.484l-1.917.882 2.37 2.837-.454-3.719zm8.487.877l-1.928-.86-.44 3.697 2.368-2.837zM16.5 3.293L15.478-.005h2.044L16.5 3.293z" fill-rule="evenodd"/></svg></span></span><span class="button-activeState"><span class="svgIcon svgIcon--clapFilled svgIcon--33px u-relative u-topNegative2 u-xs-top0"><svg class="svgIcon-use" width="33" height="33" viewBox="0 0 33 33" ><g fill-rule="evenodd"><path d="M29.58 17.1l-3.854-6.78c-.365-.543-.876-.899-1.431-.989a1.491 1.491 0 0 0-1.16.281c-.42.327-.65.736-.7 1.207v.001l3.623 6.367c2.46 4.498 1.67 8.802-2.333 12.807-.265.265-.536.505-.81.728 1.973-.222 3.474-1.286 4.45-2.263 4.166-4.165 3.875-8.6 2.215-11.36zm-4.831.82l-3.581-6.3c-.296-.439-.725-.742-1.183-.815a1.105 1.105 0 0 0-.89.213c-.647.502-.755 1.188-.33 2.098l1.825 3.858a.601.601 0 0 1-.197.747.596.596 0 0 1-.77-.067L10.178 8.21c-.508-.506-1.393-.506-1.901 0a1.335 1.335 0 0 0-.393.95c0 .36.139.698.393.95v.001l5.61 5.61a.599.599 0 1 1-.848.847l-5.606-5.606c-.001 0-.002 0-.003-.002L5.848 9.375a1.349 1.349 0 0 0-1.902 0 1.348 1.348 0 0 0 0 1.901l1.582 1.582 5.61 5.61a.6.6 0 0 1-.848.848l-5.61-5.61c-.51-.508-1.393-.508-1.9 0a1.332 1.332 0 0 0-.394.95c0 .36.139.697.393.952l2.363 2.362c.002.001.002.002.002.003l3.52 3.52a.6.6 0 0 1-.848.847l-3.522-3.523h-.001a1.336 1.336 0 0 0-.95-.393 1.345 1.345 0 0 0-.949 2.295l6.779 6.78c3.715 3.713 9.327 5.598 13.49 1.434 3.527-3.528 4.21-7.13 2.086-11.015zM11.817 7.727c.06-.328.213-.64.466-.893.64-.64 1.755-.64 2.396 0l3.232 3.232c-.82.783-1.09 1.833-.764 2.992l-5.33-5.33z"/><path d="M13.285.48l-1.916.881 2.37 2.837z"/><path d="M21.719 1.361L19.79.501l-.44 3.697z"/><path d="M16.502 3.298L15.481 0h2.043z"/></g></svg></span></span></button><div class="clapUndo u-width60 u-round u-height32 u-absolute u-borderBox u-paddingRight5 u-transition--transform200Spring u-background--brandSageLighter js-clapUndo" style="top: 14px; padding: 2px;"><button class="button button--chromeless u-baseColor--buttonNormal button--withIcon button--withSvgIcon u-floatRight"  data-action="multivote-undo" data-action-value="3275042fbd8d"><span class="svgIcon svgIcon--removeThin svgIcon--29px"><svg class="svgIcon-use" width="29" height="29" viewBox="0 0 29 29" ><path d="M20.13 8.11l-5.61 5.61-5.609-5.61-.801.801 5.61 5.61-5.61 5.61.801.8 5.61-5.609 5.61 5.61.8-.801-5.609-5.61 5.61-5.61" fill-rule="evenodd"/></svg></span></button></div></div><span class="u-textAlignCenter u-relative u-background js-actionMultirecommendCount u-flexOrderNegative1 u-height20 u-marginBottom7"><button class="button button--chromeless u-baseColor--buttonNormal js-multirecommendCountButton u-block u-marginAuto"  data-action="show-recommends" data-action-value="3275042fbd8d">30</button></span></div></li><li class="u-textAlignCenter u-marginVertical10"><button class="button button--large button--dark button--chromeless is-touchIconBlackPulse u-baseColor--buttonDark button--withIcon button--withSvgIcon"  title="Share on Twitter" aria-label="Share on Twitter" data-action="share-on-twitter" data-action-source="post_share_widget"><span class="svgIcon svgIcon--twitter svgIcon--29px"><svg class="svgIcon-use" width="29" height="29" viewBox="0 0 29 29" ><path d="M21.967 11.8c.018 5.93-4.607 11.18-11.177 11.18-2.172 0-4.25-.62-6.047-1.76l-.268.422-.038.5.186.013.168.012c.3.02.44.032.6.046 2.06-.026 3.95-.686 5.49-1.86l1.12-.85-1.4-.048c-1.57-.055-2.92-1.08-3.36-2.51l-.48.146-.05.5c.22.03.48.05.75.08.48-.02.87-.07 1.25-.15l2.33-.49-2.32-.49c-1.68-.35-2.91-1.83-2.91-3.55 0-.05 0-.01-.01.03l-.49-.1-.25.44c.63.36 1.35.57 2.07.58l1.7.04L7.4 13c-.978-.662-1.59-1.79-1.618-3.047a4.08 4.08 0 0 1 .524-1.8l-.825.07a12.188 12.188 0 0 0 8.81 4.515l.59.033-.06-.59v-.02c-.05-.43-.06-.63-.06-.87a3.617 3.617 0 0 1 6.27-2.45l.2.21.28-.06c1.01-.22 1.94-.59 2.73-1.09l-.75-.56c-.1.36-.04.89.12 1.36.23.68.58 1.13 1.17.85l-.21-.45-.42-.27c-.52.8-1.17 1.48-1.92 2L22 11l.016.28c.013.2.014.35 0 .52v.04zm.998.038c.018-.22.017-.417 0-.66l-.498.034.284.41a8.183 8.183 0 0 0 2.2-2.267l.97-1.48-1.6.755c.17-.08.3-.02.34.03a.914.914 0 0 1-.13-.292c-.1-.297-.13-.64-.1-.766l.36-1.254-1.1.695c-.69.438-1.51.764-2.41.963l.48.15a4.574 4.574 0 0 0-3.38-1.484 4.616 4.616 0 0 0-4.61 4.613c0 .29.02.51.08.984l.01.02.5-.06.03-.5c-3.17-.18-6.1-1.7-8.08-4.15l-.48-.56-.36.64c-.39.69-.62 1.48-.65 2.28.04 1.61.81 3.04 2.06 3.88l.3-.92c-.55-.02-1.11-.17-1.6-.45l-.59-.34-.14.67c-.02.08-.02.16 0 .24-.01 2.12 1.55 4.01 3.69 4.46l.1-.49-.1-.49c-.33.07-.67.12-1.03.14-.18-.02-.43-.05-.64-.07l-.76-.09.23.73c.57 1.84 2.29 3.14 4.28 3.21l-.28-.89a8.252 8.252 0 0 1-4.85 1.66c-.12-.01-.26-.02-.56-.05l-.17-.01-.18-.01L2.53 21l1.694 1.07a12.233 12.233 0 0 0 6.58 1.917c7.156 0 12.2-5.73 12.18-12.18l-.002.04z"/></svg></span></button></li><li class="u-textAlignCenter u-marginVertical10"><button class="button button--large button--dark button--chromeless is-touchIconBlackPulse u-baseColor--buttonDark button--withIcon button--withSvgIcon"  title="Share on Facebook" aria-label="Share on Facebook" data-action="share-on-facebook" data-action-source="post_share_widget"><span class="svgIcon svgIcon--facebook svgIcon--29px"><svg class="svgIcon-use" width="29" height="29" viewBox="0 0 29 29" ><path d="M16.39 23.61v-5.808h1.846a.55.55 0 0 0 .546-.48l.36-2.797a.551.551 0 0 0-.547-.62H16.39V12.67c0-.67.12-.813.828-.813h1.474a.55.55 0 0 0 .55-.55V8.803a.55.55 0 0 0-.477-.545c-.436-.06-1.36-.116-2.22-.116-2.5 0-4.13 1.62-4.13 4.248v1.513H10.56a.551.551 0 0 0-.55.55v2.797c0 .304.248.55.55.55h1.855v5.76c-4.172-.96-7.215-4.7-7.215-9.1 0-5.17 4.17-9.36 9.31-9.36 5.14 0 9.31 4.19 9.31 9.36 0 4.48-3.155 8.27-7.43 9.15M14.51 4C8.76 4 4.1 8.684 4.1 14.46c0 5.162 3.75 9.523 8.778 10.32a.55.55 0 0 0 .637-.543v-6.985a.551.551 0 0 0-.55-.55H11.11v-1.697h1.855a.55.55 0 0 0 .55-.55v-2.063c0-2.02 1.136-3.148 3.03-3.148.567 0 1.156.027 1.597.06v1.453h-.924c-1.363 0-1.93.675-1.93 1.912v1.78c0 .3.247.55.55.55h2.132l-.218 1.69H15.84c-.305 0-.55.24-.55.55v7.02c0 .33.293.59.623.54 5.135-.7 9.007-5.11 9.007-10.36C24.92 8.68 20.26 4 14.51 4"/></svg></span></button></li><li class="u-textAlignCenter u-marginVertical10"><button class="button button--large button--dark button--chromeless is-touchIconFadeInPulse u-baseColor--buttonDark button--withIcon button--withSvgIcon button--bookmark js-bookmarkButton"  title="Bookmark this story to read later" aria-label="Bookmark this story to read later" data-action="sign-up-prompt" data-sign-in-action="add-to-bookmarks" data-requires-token="true" data-redirect="https://medium.com/_/bookmark/p/3275042fbd8d" data-action-source="post_share_widget-----3275042fbd8d---------------------bookmark_sidebar"><span class="button-defaultState"><span class="svgIcon svgIcon--bookmark svgIcon--29px"><svg class="svgIcon-use" width="29" height="29" viewBox="0 0 29 29" ><path d="M19.385 4h-9.77A2.623 2.623 0 0 0 7 6.615V23.01a1.022 1.022 0 0 0 1.595.847l5.905-4.004 5.905 4.004A1.022 1.022 0 0 0 22 23.011V6.62A2.625 2.625 0 0 0 19.385 4zM21 23l-5.91-3.955-.148-.107a.751.751 0 0 0-.884 0l-.147.107L8 23V6.615C8 5.725 8.725 5 9.615 5h9.77C20.275 5 21 5.725 21 6.615V23z" fill-rule="evenodd"/></svg></span></span><span class="button-activeState"><span class="svgIcon svgIcon--bookmarkFilled svgIcon--29px"><svg class="svgIcon-use" width="29" height="29" viewBox="0 0 29 29" ><path d="M19.385 4h-9.77A2.623 2.623 0 0 0 7 6.615V23.01a1.022 1.022 0 0 0 1.595.847l5.905-4.004 5.905 4.004A1.022 1.022 0 0 0 22 23.011V6.62A2.625 2.625 0 0 0 19.385 4z" fill-rule="evenodd"/></svg></span></span></button></li></ul></div></div><div class="u-fixed u-bottom0 u-sizeFullWidth u-backgroundWhite u-boxShadowTop u-borderBox u-paddingTop10 u-paddingBottom10 u-zIndexMetabar u-xs-paddingLeft10 u-xs-paddingRight10 js-stickyFooter"><div class="u-maxWidth700 u-marginAuto u-flexCenter"><div class="u-fontSize16 u-flex1 u-flexCenter"><div class="u-flex0 u-inlineBlock u-paddingRight20 u-xs-paddingRight10"><a class="link u-baseColor--link avatar avatar--roundedRectangle"   href="https://towardsdatascience.com" title="Go to Towards Data Science" aria-label="Go to Towards Data Science" data-collection-slug="towards-data-science"><img src="https://cdn-images-1.medium.com/fit/c/80/80/1*F0LADxTtsKOgmPa-_7iUEQ.jpeg" class="avatar-image avatar-image--smaller" alt="Towards Data Science"></a></div><div class="u-flex1 u-inlineBlock"><div class="u-xs-hide">Never miss a story from<strong> Towards Data Science</strong>, when you sign up for Medium. <a class="link u-baseColor--link link--accent u-accentColor--textNormal u-accentColor--textDarken"   href="https://medium.com/@Medium/personalize-your-medium-experience-with-users-publications-tags-26a41ab1ee0c#.hx4zuv3mg" data-action-source="sticky_footer">Learn more</a></div><div class="u-xs-show">Never miss a story from<strong> Towards Data Science</strong></div></div></div><div class="u-marginLeft50 u-xs-marginAuto"><button class="button button--primary button--dark is-active u-noUserSelect button--withChrome u-accentColor--buttonDark u-uiTextSemibold u-textUppercase u-fontSize12 button--followCollection js-followCollectionButton"  data-action="sign-up-prompt" data-sign-in-action="toggle-subscribe-collection" data-requires-token="true" data-redirect="https://medium.com/_/subscribe/collection/towards-data-science" data-action-source="sticky_footer----7f60cf5620c9----------------------follow_metabar"><span class="button-label  button-defaultState js-buttonLabel">Get updates</span><span class="button-label button-activeState">Get updates</span></button></div></div></div><style class="js-collectionStyle">
.u-accentColor--borderLight {border-color: #668AAA !important;}
.u-accentColor--borderNormal {border-color: #668AAA !important;}
.u-accentColor--borderDark {border-color: #5A7690 !important;}
.u-accentColor--iconLight .svgIcon,.u-accentColor--iconLight.svgIcon {fill: #668AAA !important;}
.u-accentColor--iconNormal .svgIcon,.u-accentColor--iconNormal.svgIcon {fill: #668AAA !important;}
.u-accentColor--iconDark .svgIcon,.u-accentColor--iconDark.svgIcon {fill: #5A7690 !important;}
.u-accentColor--textNormal {color: #5A7690 !important;}
.u-accentColor--hoverTextNormal:hover {color: #5A7690 !important;}
.u-accentColor--textNormal.u-accentColor--textDarken:hover {color: #546C83 !important;}
.u-accentColor--textDark {color: #546C83 !important;}
.u-accentColor--backgroundLight {background-color: #668AAA !important;}
.u-accentColor--backgroundNormal {background-color: #668AAA !important;}
.u-accentColor--backgroundDark {background-color: #5A7690 !important;}
.u-accentColor--buttonDark {border-color: #5A7690 !important; color: #546C83 !important;}
.u-accentColor--buttonDark:hover {border-color: #546C83 !important;}
.u-accentColor--buttonDark .icon:before,.u-accentColor--buttonDark .svgIcon{color: #5A7690 !important; fill: #5A7690 !important;}
.u-accentColor--buttonNormal:not(.clapButton--largePill) {border-color: #668AAA !important; color: #5A7690 !important;}
.u-accentColor--buttonNormal:hover {border-color: #5A7690 !important;}
.u-accentColor--buttonNormal .icon:before,.u-accentColor--buttonNormal .svgIcon{color: #668AAA !important; fill: #668AAA !important;}
.u-accentColor--buttonNormal.button--filled .icon:before,.u-accentColor--buttonNormal.button--filled .svgIcon{color: rgba(255, 255, 255, 1) !important; fill: rgba(255, 255, 255, 1) !important;}
.u-accentColor--buttonDark.button--filled,.u-accentColor--buttonDark.button--withChrome.is-active,.u-accentColor--fillWhenActive.is-active {background-color: #5A7690 !important; border-color: #5A7690 !important; color: rgba(255, 255, 255, 1) !important; fill: rgba(255, 255, 255, 1) !important;}
.u-accentColor--buttonNormal.button--filled:not(.clapButton--largePill),.u-accentColor--buttonNormal.button--withChrome.is-active:not(.clapButton--largePill) {background-color: #668AAA !important; border-color: #668AAA !important; color: rgba(255, 255, 255, 1) !important; fill: rgba(255, 255, 255, 1) !important;}
.postArticle.is-withAccentColors .markup--user,.postArticle.is-withAccentColors .markup--query {color: #5A7690 !important;}.u-tintBgColor {background-color: rgba(53, 88, 118, 1) !important;}.u-tintBgColor .u-fadeLeft:before {background-image: linear-gradient(to right, rgba(53, 88, 118, 1) 0%, rgba(53, 88, 118, 0) 100%) !important;}.u-tintBgColor .u-fadeRight:after {background-image: linear-gradient(to right, rgba(53, 88, 118, 0) 0%, rgba(53, 88, 118, 1) 100%) !important;}
.u-tintSpectrum .u-baseColor--borderLight {border-color: #9FB3C6 !important;}
.u-tintSpectrum .u-baseColor--borderNormal {border-color: #C5D2E1 !important;}
.u-tintSpectrum .u-baseColor--borderDark {border-color: #E9F1FA !important;}
.u-tintSpectrum .u-baseColor--iconLight .svgIcon,.u-tintSpectrum .u-baseColor--iconLight.svgIcon {fill: #9FB3C6 !important;}
.u-tintSpectrum .u-baseColor--iconNormal .svgIcon,.u-tintSpectrum .u-baseColor--iconNormal.svgIcon {fill: #C5D2E1 !important;}
.u-tintSpectrum .u-baseColor--iconDark .svgIcon,.u-tintSpectrum .u-baseColor--iconDark.svgIcon {fill: #E9F1FA !important;}
.u-tintSpectrum .u-baseColor--textNormal {color: #C5D2E1 !important;}
.u-tintSpectrum .u-baseColor--textNormal.u-baseColor--textDarken:hover {color: #FBFFFF !important;}
.u-tintSpectrum .u-baseColor--textDark {color: #FBFFFF !important;}
.u-tintSpectrum .u-baseColor--textDarker {color: #FBFFFF !important;}
.u-tintSpectrum .u-baseColor--backgroundLight {background-color: #9FB3C6 !important;}
.u-tintSpectrum .u-baseColor--backgroundNormal {background-color: #C5D2E1 !important;}
.u-tintSpectrum .u-baseColor--backgroundDark {background-color: #E9F1FA !important;}
.u-tintSpectrum .u-baseColor--buttonLight {border-color: #9FB3C6 !important; color: #9FB3C6 !important;}
.u-tintSpectrum .u-baseColor--buttonLight:hover {border-color: #9FB3C6 !important;}
.u-tintSpectrum .u-baseColor--buttonLight .icon:before,.u-tintSpectrum .u-baseColor--buttonLight .svgIcon {color: #9FB3C6 !important; fill: #9FB3C6 !important;}
.u-tintSpectrum .u-baseColor--buttonDark {border-color: #E9F1FA !important; color: #FBFFFF !important;}
.u-tintSpectrum .u-baseColor--buttonDark:hover {border-color: #FBFFFF !important;}
.u-tintSpectrum .u-baseColor--buttonDark .icon:before,.u-tintSpectrum .u-baseColor--buttonDark .svgIcon {color: #E9F1FA !important; fill: #E9F1FA !important;}
.u-tintSpectrum .u-baseColor--buttonNormal {border-color: #C5D2E1 !important; color: #C5D2E1 !important;}
.u-tintSpectrum .u-baseColor--buttonNormal:hover {border-color: #E9F1FA !important;}
.u-tintSpectrum .u-baseColor--buttonNormal .icon:before,.u-tintSpectrum .u-baseColor--buttonNormal .svgIcon {color: #C5D2E1 !important; fill: #C5D2E1 !important;}
.u-tintSpectrum .u-baseColor--buttonDark.button--filled,.u-tintSpectrum .u-baseColor--buttonDark.button--withChrome.is-active {background-color: #E9F1FA !important; border-color: #E9F1FA !important; color: rgba(53, 88, 118, 1) !important; fill: rgba(53, 88, 118, 1) !important;}
.u-tintSpectrum .u-baseColor--buttonNormal.button--filled,.u-tintSpectrum .u-baseColor--buttonNormal.button--withChrome.is-active {background-color: #C5D2E1 !important; border-color: #C5D2E1 !important; color: rgba(53, 88, 118, 1) !important; fill: rgba(53, 88, 118, 1) !important;}
.u-tintSpectrum .u-baseColor--link {color: #C5D2E1 !important;}
.u-tintSpectrum .u-baseColor--link.link--darkenOnHover:hover {color: #FBFFFF !important;}
.u-tintSpectrum .u-baseColor--link.link--darken:hover,.u-tintSpectrum .u-baseColor--link.link--darken:focus,.u-tintSpectrum .u-baseColor--link.link--darken:active {color: #FBFFFF !important;}
.u-tintSpectrum .u-baseColor--link.link--dark {color: #FBFFFF !important;}
.u-tintSpectrum .u-baseColor--link.link--dark.link--darken:hover,.u-tintSpectrum .u-baseColor--link.link--dark.link--darken:focus,.u-tintSpectrum .u-baseColor--link.link--dark.link--darken:active {color: #FBFFFF !important;}
.u-tintSpectrum .u-baseColor--link.link--darker {color: #FBFFFF !important;}
.u-tintSpectrum .u-baseColor--placeholderNormal ::-webkit-input-placeholder {color: #9FB3C6;}
.u-tintSpectrum .u-baseColor--placeholderNormal ::-moz-placeholder {color: #9FB3C6;}
.u-tintSpectrum .u-baseColor--placeholderNormal :-ms-input-placeholder {color: #9FB3C6;}
.u-tintSpectrum .svgIcon--logoNew path:nth-child(1) {stroke: none !important; fill: #637F99 !important;}
.u-tintSpectrum .svgIcon--logoNew path:nth-child(2) {stroke: none !important; fill: #7791A8 !important;}
.u-tintSpectrum .svgIcon--logoNew path:nth-child(3) {stroke: none !important; fill: #9FB3C6 !important;}
.u-tintSpectrum .svgIcon--logoNew path:nth-child(4) {stroke: none !important; fill: #C5D2E1 !important;}
.u-tintSpectrum .svgIcon--logoWordmark {stroke: none !important; fill: #FBFFFF !important;}
.u-tintSpectrum .svgIcon--logoMonogram {stroke: none !important; fill: #FBFFFF !important;}
.u-tintSpectrum  .ui-h1,.u-tintSpectrum  .ui-h2,.u-tintSpectrum  .ui-h3,.u-tintSpectrum  .ui-h4,.u-tintSpectrum  .ui-brand1,.u-tintSpectrum  .ui-brand2,.u-tintSpectrum  .ui-captionStrong {color: #FBFFFF !important; fill: #FBFFFF !important;}
.u-tintSpectrum  .ui-body,.u-tintSpectrum  .ui-caps {color: #FBFFFF !important; fill: #FBFFFF !important;}
.u-tintSpectrum  .ui-summary,.u-tintSpectrum  .ui-caption {color: #9FB3C6 !important; fill: #9FB3C6 !important;}
.u-tintSpectrum .u-accentColor--borderLight {border-color: #9FB3C6 !important;}
.u-tintSpectrum .u-accentColor--borderNormal {border-color: #C5D2E1 !important;}
.u-tintSpectrum .u-accentColor--borderDark {border-color: #E9F1FA !important;}
.u-tintSpectrum .u-accentColor--iconLight .svgIcon,.u-tintSpectrum .u-accentColor--iconLight.svgIcon {fill: #9FB3C6 !important;}
.u-tintSpectrum .u-accentColor--iconNormal .svgIcon,.u-tintSpectrum .u-accentColor--iconNormal.svgIcon {fill: #C5D2E1 !important;}
.u-tintSpectrum .u-accentColor--iconDark .svgIcon,.u-tintSpectrum .u-accentColor--iconDark.svgIcon {fill: #E9F1FA !important;}
.u-tintSpectrum .u-accentColor--textNormal {color: #C5D2E1 !important;}
.u-tintSpectrum .u-accentColor--hoverTextNormal:hover {color: #C5D2E1 !important;}
.u-tintSpectrum .u-accentColor--textNormal.u-accentColor--textDarken:hover {color: #FBFFFF !important;}
.u-tintSpectrum .u-accentColor--textDark {color: #FBFFFF !important;}
.u-tintSpectrum .u-accentColor--backgroundLight {background-color: #9FB3C6 !important;}
.u-tintSpectrum .u-accentColor--backgroundNormal {background-color: #C5D2E1 !important;}
.u-tintSpectrum .u-accentColor--backgroundDark {background-color: #E9F1FA !important;}
.u-tintSpectrum .u-accentColor--buttonDark {border-color: #E9F1FA !important; color: #FBFFFF !important;}
.u-tintSpectrum .u-accentColor--buttonDark:hover {border-color: #FBFFFF !important;}
.u-tintSpectrum .u-accentColor--buttonDark .icon:before,.u-tintSpectrum .u-accentColor--buttonDark .svgIcon{color: #E9F1FA !important; fill: #E9F1FA !important;}
.u-tintSpectrum .u-accentColor--buttonNormal:not(.clapButton--largePill) {border-color: #C5D2E1 !important; color: #C5D2E1 !important;}
.u-tintSpectrum .u-accentColor--buttonNormal:hover {border-color: #E9F1FA !important;}
.u-tintSpectrum .u-accentColor--buttonNormal .icon:before,.u-tintSpectrum .u-accentColor--buttonNormal .svgIcon{color: #C5D2E1 !important; fill: #C5D2E1 !important;}
.u-tintSpectrum .u-accentColor--buttonNormal.button--filled .icon:before,.u-tintSpectrum .u-accentColor--buttonNormal.button--filled .svgIcon{color: rgba(53, 88, 118, 1) !important; fill: rgba(53, 88, 118, 1) !important;}
.u-tintSpectrum .u-accentColor--buttonDark.button--filled,.u-tintSpectrum .u-accentColor--buttonDark.button--withChrome.is-active,.u-tintSpectrum .u-accentColor--fillWhenActive.is-active {background-color: #E9F1FA !important; border-color: #E9F1FA !important; color: rgba(53, 88, 118, 1) !important; fill: rgba(53, 88, 118, 1) !important;}
.u-tintSpectrum .u-accentColor--buttonNormal.button--filled:not(.clapButton--largePill),.u-tintSpectrum .u-accentColor--buttonNormal.button--withChrome.is-active:not(.clapButton--largePill) {background-color: #C5D2E1 !important; border-color: #C5D2E1 !important; color: rgba(53, 88, 118, 1) !important; fill: rgba(53, 88, 118, 1) !important;}
.u-tintSpectrum .postArticle.is-withAccentColors .markup--user,.u-tintSpectrum .postArticle.is-withAccentColors .markup--query {color: #C5D2E1 !important;}
.u-accentColor--highlightFaint {background-color: rgba(233, 242, 253, 1) !important;}
.u-accentColor--highlightStrong.is-active .svgIcon {fill: rgba(200, 228, 255, 1) !important;}
.postArticle.is-withAccentColors .markup--quote.is-other {background-color: rgba(233, 242, 253, 1) !important;}
body.is-withMagicUnderlines .postArticle.is-withAccentColors .markup--quote.is-other {background-color: transparent !important; background-image: linear-gradient(to bottom, rgba(233, 242, 253, 1), rgba(233, 242, 253, 1));}
.postArticle.is-withAccentColors .markup--quote.is-me {background-color: rgba(215, 235, 254, 1) !important;}
body.is-withMagicUnderlines .postArticle.is-withAccentColors .markup--quote.is-me {background-color: transparent !important; background-image: linear-gradient(to bottom, rgba(215, 235, 254, 1), rgba(215, 235, 254, 1));}
.postArticle.is-withAccentColors .markup--quote.is-targeted {background-color: rgba(200, 228, 255, 1) !important;}
body.is-withMagicUnderlines .postArticle.is-withAccentColors .markup--quote.is-targeted {background-color: transparent !important; background-image: linear-gradient(to bottom, rgba(200, 228, 255, 1), rgba(200, 228, 255, 1));}
.postArticle.is-withAccentColors .markup--quote.is-selected {background-color: rgba(200, 228, 255, 1) !important;}
body.is-withMagicUnderlines .postArticle.is-withAccentColors .markup--quote.is-selected {background-color: transparent !important; background-image: linear-gradient(to bottom, rgba(200, 228, 255, 1), rgba(200, 228, 255, 1));}
.postArticle.is-withAccentColors .markup--highlight {background-color: rgba(200, 228, 255, 1) !important;}
body.is-withMagicUnderlines .postArticle.is-withAccentColors .markup--highlight {background-color: transparent !important; background-image: linear-gradient(to bottom, rgba(200, 228, 255, 1), rgba(200, 228, 255, 1));}.u-baseColor--iconNormal.avatar-halo {fill: rgba(0, 0, 0, 0.4980392156862745) !important;}</style><style class="js-collectionStyleConstant">.u-imageBgColor {background-color: rgba(0, 0, 0, 0.24705882352941178);}
.u-imageSpectrum .u-baseColor--borderLight {border-color: rgba(255, 255, 255, 0.6980392156862745) !important;}
.u-imageSpectrum .u-baseColor--borderNormal {border-color: rgba(255, 255, 255, 0.8980392156862745) !important;}
.u-imageSpectrum .u-baseColor--borderDark {border-color: rgba(255, 255, 255, 0.9490196078431372) !important;}
.u-imageSpectrum .u-baseColor--iconLight .svgIcon,.u-imageSpectrum .u-baseColor--iconLight.svgIcon {fill: rgba(255, 255, 255, 0.8) !important;}
.u-imageSpectrum .u-baseColor--iconNormal .svgIcon,.u-imageSpectrum .u-baseColor--iconNormal.svgIcon {fill: rgba(255, 255, 255, 0.9490196078431372) !important;}
.u-imageSpectrum .u-baseColor--iconDark .svgIcon,.u-imageSpectrum .u-baseColor--iconDark.svgIcon {fill: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-baseColor--textNormal {color: rgba(255, 255, 255, 0.9490196078431372) !important;}
.u-imageSpectrum .u-baseColor--textNormal.u-baseColor--textDarken:hover {color: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-baseColor--textDark {color: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-baseColor--textDarker {color: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-baseColor--backgroundLight {background-color: rgba(255, 255, 255, 0.8980392156862745) !important;}
.u-imageSpectrum .u-baseColor--backgroundNormal {background-color: rgba(255, 255, 255, 0.9490196078431372) !important;}
.u-imageSpectrum .u-baseColor--backgroundDark {background-color: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-baseColor--buttonLight {border-color: rgba(255, 255, 255, 0.6980392156862745) !important; color: rgba(255, 255, 255, 0.8) !important;}
.u-imageSpectrum .u-baseColor--buttonLight:hover {border-color: rgba(255, 255, 255, 0.6980392156862745) !important;}
.u-imageSpectrum .u-baseColor--buttonLight .icon:before,.u-imageSpectrum .u-baseColor--buttonLight .svgIcon {color: rgba(255, 255, 255, 0.8) !important; fill: rgba(255, 255, 255, 0.8) !important;}
.u-imageSpectrum .u-baseColor--buttonDark {border-color: rgba(255, 255, 255, 0.9490196078431372) !important; color: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-baseColor--buttonDark:hover {border-color: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-baseColor--buttonDark .icon:before,.u-imageSpectrum .u-baseColor--buttonDark .svgIcon {color: rgba(255, 255, 255, 1) !important; fill: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-baseColor--buttonNormal {border-color: rgba(255, 255, 255, 0.8980392156862745) !important; color: rgba(255, 255, 255, 0.9490196078431372) !important;}
.u-imageSpectrum .u-baseColor--buttonNormal:hover {border-color: rgba(255, 255, 255, 0.9490196078431372) !important;}
.u-imageSpectrum .u-baseColor--buttonNormal .icon:before,.u-imageSpectrum .u-baseColor--buttonNormal .svgIcon {color: rgba(255, 255, 255, 0.9490196078431372) !important; fill: rgba(255, 255, 255, 0.9490196078431372) !important;}
.u-imageSpectrum .u-baseColor--buttonDark.button--filled,.u-imageSpectrum .u-baseColor--buttonDark.button--withChrome.is-active {background-color: rgba(255, 255, 255, 1) !important; border-color: rgba(255, 255, 255, 1) !important; color: rgba(0, 0, 0, 0.24705882352941178) !important; fill: rgba(0, 0, 0, 0.24705882352941178) !important;}
.u-imageSpectrum .u-baseColor--buttonNormal.button--filled,.u-imageSpectrum .u-baseColor--buttonNormal.button--withChrome.is-active {background-color: rgba(255, 255, 255, 0.9490196078431372) !important; border-color: rgba(255, 255, 255, 0.9490196078431372) !important; color: rgba(0, 0, 0, 0.24705882352941178) !important; fill: rgba(0, 0, 0, 0.24705882352941178) !important;}
.u-imageSpectrum .u-baseColor--link {color: rgba(255, 255, 255, 0.9490196078431372) !important;}
.u-imageSpectrum .u-baseColor--link.link--darkenOnHover:hover {color: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-baseColor--link.link--darken:hover,.u-imageSpectrum .u-baseColor--link.link--darken:focus,.u-imageSpectrum .u-baseColor--link.link--darken:active {color: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-baseColor--link.link--dark {color: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-baseColor--link.link--dark.link--darken:hover,.u-imageSpectrum .u-baseColor--link.link--dark.link--darken:focus,.u-imageSpectrum .u-baseColor--link.link--dark.link--darken:active {color: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-baseColor--link.link--darker {color: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-baseColor--placeholderNormal ::-webkit-input-placeholder {color: rgba(255, 255, 255, 0.8);}
.u-imageSpectrum .u-baseColor--placeholderNormal ::-moz-placeholder {color: rgba(255, 255, 255, 0.8);}
.u-imageSpectrum .u-baseColor--placeholderNormal :-ms-input-placeholder {color: rgba(255, 255, 255, 0.8);}
.u-imageSpectrum .svgIcon--logoNew path:nth-child(1) {stroke: none !important; fill: rgba(255, 255, 255, 0.4) !important;}
.u-imageSpectrum .svgIcon--logoNew path:nth-child(2) {stroke: none !important; fill: rgba(255, 255, 255, 0.4980392156862745) !important;}
.u-imageSpectrum .svgIcon--logoNew path:nth-child(3) {stroke: none !important; fill: rgba(255, 255, 255, 0.6980392156862745) !important;}
.u-imageSpectrum .svgIcon--logoNew path:nth-child(4) {stroke: none !important; fill: rgba(255, 255, 255, 0.8980392156862745) !important;}
.u-imageSpectrum .svgIcon--logoWordmark {stroke: none !important; fill: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .svgIcon--logoMonogram {stroke: none !important; fill: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum  .ui-h1,.u-imageSpectrum  .ui-h2,.u-imageSpectrum  .ui-h3,.u-imageSpectrum  .ui-h4,.u-imageSpectrum  .ui-brand1,.u-imageSpectrum  .ui-brand2,.u-imageSpectrum  .ui-captionStrong {color: rgba(255, 255, 255, 1) !important; fill: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum  .ui-body,.u-imageSpectrum  .ui-caps {color: rgba(255, 255, 255, 1) !important; fill: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum  .ui-summary,.u-imageSpectrum  .ui-caption {color: rgba(255, 255, 255, 0.8) !important; fill: rgba(255, 255, 255, 0.8) !important;}
.u-imageSpectrum .u-accentColor--borderLight {border-color: rgba(255, 255, 255, 0.6980392156862745) !important;}
.u-imageSpectrum .u-accentColor--borderNormal {border-color: rgba(255, 255, 255, 0.8980392156862745) !important;}
.u-imageSpectrum .u-accentColor--borderDark {border-color: rgba(255, 255, 255, 0.9490196078431372) !important;}
.u-imageSpectrum .u-accentColor--iconLight .svgIcon,.u-imageSpectrum .u-accentColor--iconLight.svgIcon {fill: rgba(255, 255, 255, 0.8) !important;}
.u-imageSpectrum .u-accentColor--iconNormal .svgIcon,.u-imageSpectrum .u-accentColor--iconNormal.svgIcon {fill: rgba(255, 255, 255, 0.9490196078431372) !important;}
.u-imageSpectrum .u-accentColor--iconDark .svgIcon,.u-imageSpectrum .u-accentColor--iconDark.svgIcon {fill: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-accentColor--textNormal {color: rgba(255, 255, 255, 0.9490196078431372) !important;}
.u-imageSpectrum .u-accentColor--hoverTextNormal:hover {color: rgba(255, 255, 255, 0.9490196078431372) !important;}
.u-imageSpectrum .u-accentColor--textNormal.u-accentColor--textDarken:hover {color: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-accentColor--textDark {color: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-accentColor--backgroundLight {background-color: rgba(255, 255, 255, 0.8980392156862745) !important;}
.u-imageSpectrum .u-accentColor--backgroundNormal {background-color: rgba(255, 255, 255, 0.9490196078431372) !important;}
.u-imageSpectrum .u-accentColor--backgroundDark {background-color: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-accentColor--buttonDark {border-color: rgba(255, 255, 255, 0.9490196078431372) !important; color: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-accentColor--buttonDark:hover {border-color: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-accentColor--buttonDark .icon:before,.u-imageSpectrum .u-accentColor--buttonDark .svgIcon{color: rgba(255, 255, 255, 1) !important; fill: rgba(255, 255, 255, 1) !important;}
.u-imageSpectrum .u-accentColor--buttonNormal:not(.clapButton--largePill) {border-color: rgba(255, 255, 255, 0.8980392156862745) !important; color: rgba(255, 255, 255, 0.9490196078431372) !important;}
.u-imageSpectrum .u-accentColor--buttonNormal:hover {border-color: rgba(255, 255, 255, 0.9490196078431372) !important;}
.u-imageSpectrum .u-accentColor--buttonNormal .icon:before,.u-imageSpectrum .u-accentColor--buttonNormal .svgIcon{color: rgba(255, 255, 255, 0.9490196078431372) !important; fill: rgba(255, 255, 255, 0.9490196078431372) !important;}
.u-imageSpectrum .u-accentColor--buttonNormal.button--filled .icon:before,.u-imageSpectrum .u-accentColor--buttonNormal.button--filled .svgIcon{color: rgba(0, 0, 0, 0.24705882352941178) !important; fill: rgba(0, 0, 0, 0.24705882352941178) !important;}
.u-imageSpectrum .u-accentColor--buttonDark.button--filled,.u-imageSpectrum .u-accentColor--buttonDark.button--withChrome.is-active,.u-imageSpectrum .u-accentColor--fillWhenActive.is-active {background-color: rgba(255, 255, 255, 1) !important; border-color: rgba(255, 255, 255, 1) !important; color: rgba(0, 0, 0, 0.24705882352941178) !important; fill: rgba(0, 0, 0, 0.24705882352941178) !important;}
.u-imageSpectrum .u-accentColor--buttonNormal.button--filled:not(.clapButton--largePill),.u-imageSpectrum .u-accentColor--buttonNormal.button--withChrome.is-active:not(.clapButton--largePill) {background-color: rgba(255, 255, 255, 0.9490196078431372) !important; border-color: rgba(255, 255, 255, 0.9490196078431372) !important; color: rgba(0, 0, 0, 0.24705882352941178) !important; fill: rgba(0, 0, 0, 0.24705882352941178) !important;}
.u-imageSpectrum .postArticle.is-withAccentColors .markup--user,.u-imageSpectrum .postArticle.is-withAccentColors .markup--query {color: rgba(255, 255, 255, 0.9490196078431372) !important;}
.u-imageSpectrum .u-accentColor--highlightFaint {background-color: rgba(255, 255, 255, 0.2) !important;}
.u-imageSpectrum .u-accentColor--highlightStrong.is-active .svgIcon {fill: rgba(255, 255, 255, 0.6) !important;}
.postArticle.is-withAccentColors .u-imageSpectrum .markup--quote.is-other {background-color: rgba(255, 255, 255, 0.2) !important;}
body.is-withMagicUnderlines .postArticle.is-withAccentColors .u-imageSpectrum .markup--quote.is-other {background-color: transparent !important; background-image: linear-gradient(to bottom, rgba(255, 255, 255, 0.2), rgba(255, 255, 255, 0.2));}
.postArticle.is-withAccentColors .u-imageSpectrum .markup--quote.is-me {background-color: rgba(255, 255, 255, 0.4) !important;}
body.is-withMagicUnderlines .postArticle.is-withAccentColors .u-imageSpectrum .markup--quote.is-me {background-color: transparent !important; background-image: linear-gradient(to bottom, rgba(255, 255, 255, 0.4), rgba(255, 255, 255, 0.4));}
.postArticle.is-withAccentColors .u-imageSpectrum .markup--quote.is-targeted {background-color: rgba(255, 255, 255, 0.6) !important;}
body.is-withMagicUnderlines .postArticle.is-withAccentColors .u-imageSpectrum .markup--quote.is-targeted {background-color: transparent !important; background-image: linear-gradient(to bottom, rgba(255, 255, 255, 0.6), rgba(255, 255, 255, 0.6));}
.postArticle.is-withAccentColors .u-imageSpectrum .markup--quote.is-selected {background-color: rgba(255, 255, 255, 0.6) !important;}
body.is-withMagicUnderlines .postArticle.is-withAccentColors .u-imageSpectrum .markup--quote.is-selected {background-color: transparent !important; background-image: linear-gradient(to bottom, rgba(255, 255, 255, 0.6), rgba(255, 255, 255, 0.6));}
.postArticle.is-withAccentColors .u-imageSpectrum .markup--highlight {background-color: rgba(255, 255, 255, 0.6) !important;}
body.is-withMagicUnderlines .postArticle.is-withAccentColors .u-imageSpectrum .markup--highlight {background-color: transparent !important; background-image: linear-gradient(to bottom, rgba(255, 255, 255, 0.6), rgba(255, 255, 255, 0.6));}.u-resetSpectrum .u-tintBgColor {background-color: rgba(255, 255, 255, 1) !important;}.u-resetSpectrum .u-tintBgColor .u-fadeLeft:before {background-image: linear-gradient(to right, rgba(255, 255, 255, 1) 0%, rgba(255, 255, 255, 0) 100%) !important;}.u-resetSpectrum .u-tintBgColor .u-fadeRight:after {background-image: linear-gradient(to right, rgba(255, 255, 255, 0) 0%, rgba(255, 255, 255, 1) 100%) !important;}
.u-resetSpectrum .u-baseColor--borderLight {border-color: rgba(0, 0, 0, 0.2980392156862745) !important;}
.u-resetSpectrum .u-baseColor--borderNormal {border-color: rgba(0, 0, 0, 0.4980392156862745) !important;}
.u-resetSpectrum .u-baseColor--borderDark {border-color: rgba(0, 0, 0, 0.6) !important;}
.u-resetSpectrum .u-baseColor--iconLight .svgIcon,.u-resetSpectrum .u-baseColor--iconLight.svgIcon {fill: rgba(0, 0, 0, 0.2980392156862745) !important;}
.u-resetSpectrum .u-baseColor--iconNormal .svgIcon,.u-resetSpectrum .u-baseColor--iconNormal.svgIcon {fill: rgba(0, 0, 0, 0.4980392156862745) !important;}
.u-resetSpectrum .u-baseColor--iconDark .svgIcon,.u-resetSpectrum .u-baseColor--iconDark.svgIcon {fill: rgba(0, 0, 0, 0.6) !important;}
.u-resetSpectrum .u-baseColor--textNormal {color: rgba(0, 0, 0, 0.4980392156862745) !important;}
.u-resetSpectrum .u-baseColor--textNormal.u-baseColor--textDarken:hover {color: rgba(0, 0, 0, 0.6) !important;}
.u-resetSpectrum .u-baseColor--textDark {color: rgba(0, 0, 0, 0.6) !important;}
.u-resetSpectrum .u-baseColor--textDarker {color: rgba(0, 0, 0, 0.8) !important;}
.u-resetSpectrum .u-baseColor--backgroundLight {background-color: rgba(0, 0, 0, 0.09803921568627451) !important;}
.u-resetSpectrum .u-baseColor--backgroundNormal {background-color: rgba(0, 0, 0, 0.2) !important;}
.u-resetSpectrum .u-baseColor--backgroundDark {background-color: rgba(0, 0, 0, 0.2980392156862745) !important;}
.u-resetSpectrum .u-baseColor--buttonLight {border-color: rgba(0, 0, 0, 0.2980392156862745) !important; color: rgba(0, 0, 0, 0.2980392156862745) !important;}
.u-resetSpectrum .u-baseColor--buttonLight:hover {border-color: rgba(0, 0, 0, 0.2980392156862745) !important;}
.u-resetSpectrum .u-baseColor--buttonLight .icon:before,.u-resetSpectrum .u-baseColor--buttonLight .svgIcon {color: rgba(0, 0, 0, 0.2980392156862745) !important; fill: rgba(0, 0, 0, 0.2980392156862745) !important;}
.u-resetSpectrum .u-baseColor--buttonDark {border-color: rgba(0, 0, 0, 0.6) !important; color: rgba(0, 0, 0, 0.6) !important;}
.u-resetSpectrum .u-baseColor--buttonDark:hover {border-color: rgba(0, 0, 0, 0.8) !important;}
.u-resetSpectrum .u-baseColor--buttonDark .icon:before,.u-resetSpectrum .u-baseColor--buttonDark .svgIcon {color: rgba(0, 0, 0, 0.6) !important; fill: rgba(0, 0, 0, 0.6) !important;}
.u-resetSpectrum .u-baseColor--buttonNormal {border-color: rgba(0, 0, 0, 0.4980392156862745) !important; color: rgba(0, 0, 0, 0.4980392156862745) !important;}
.u-resetSpectrum .u-baseColor--buttonNormal:hover {border-color: rgba(0, 0, 0, 0.6) !important;}
.u-resetSpectrum .u-baseColor--buttonNormal .icon:before,.u-resetSpectrum .u-baseColor--buttonNormal .svgIcon {color: rgba(0, 0, 0, 0.4980392156862745) !important; fill: rgba(0, 0, 0, 0.4980392156862745) !important;}
.u-resetSpectrum .u-baseColor--buttonDark.button--filled,.u-resetSpectrum .u-baseColor--buttonDark.button--withChrome.is-active {background-color: rgba(0, 0, 0, 0.2980392156862745) !important; border-color: rgba(0, 0, 0, 0.2980392156862745) !important; color: rgba(255, 255, 255, 1) !important; fill: rgba(255, 255, 255, 1) !important;}
.u-resetSpectrum .u-baseColor--buttonNormal.button--filled,.u-resetSpectrum .u-baseColor--buttonNormal.button--withChrome.is-active {background-color: rgba(0, 0, 0, 0.2) !important; border-color: rgba(0, 0, 0, 0.2) !important; color: rgba(255, 255, 255, 1) !important; fill: rgba(255, 255, 255, 1) !important;}
.u-resetSpectrum .u-baseColor--link {color: rgba(0, 0, 0, 0.4980392156862745) !important;}
.u-resetSpectrum .u-baseColor--link.link--darkenOnHover:hover {color: rgba(0, 0, 0, 0.6) !important;}
.u-resetSpectrum .u-baseColor--link.link--darken:hover,.u-resetSpectrum .u-baseColor--link.link--darken:focus,.u-resetSpectrum .u-baseColor--link.link--darken:active {color: rgba(0, 0, 0, 0.6) !important;}
.u-resetSpectrum .u-baseColor--link.link--dark {color: rgba(0, 0, 0, 0.6) !important;}
.u-resetSpectrum .u-baseColor--link.link--dark.link--darken:hover,.u-resetSpectrum .u-baseColor--link.link--dark.link--darken:focus,.u-resetSpectrum .u-baseColor--link.link--dark.link--darken:active {color: rgba(0, 0, 0, 0.8) !important;}
.u-resetSpectrum .u-baseColor--link.link--darker {color: rgba(0, 0, 0, 0.8) !important;}
.u-resetSpectrum .u-baseColor--placeholderNormal ::-webkit-input-placeholder {color: rgba(0, 0, 0, 0.2980392156862745);}
.u-resetSpectrum .u-baseColor--placeholderNormal ::-moz-placeholder {color: rgba(0, 0, 0, 0.2980392156862745);}
.u-resetSpectrum .u-baseColor--placeholderNormal :-ms-input-placeholder {color: rgba(0, 0, 0, 0.2980392156862745);}
.u-resetSpectrum .svgIcon--logoNew path:nth-child(1) {stroke: none !important; fill: rgba(0, 0, 0, 0.2) !important;}
.u-resetSpectrum .svgIcon--logoNew path:nth-child(2) {stroke: none !important; fill: rgba(0, 0, 0, 0.2980392156862745) !important;}
.u-resetSpectrum .svgIcon--logoNew path:nth-child(3) {stroke: none !important; fill: rgba(0, 0, 0, 0.4) !important;}
.u-resetSpectrum .svgIcon--logoNew path:nth-child(4) {stroke: none !important; fill: rgba(0, 0, 0, 0.4980392156862745) !important;}
.u-resetSpectrum .svgIcon--logoWordmark {stroke: none !important; fill: rgba(0, 0, 0, 0.6) !important;}
.u-resetSpectrum .svgIcon--logoMonogram {stroke: none !important; fill: rgba(0, 0, 0, 0.6) !important;}
.u-resetSpectrum  .ui-h1,.u-resetSpectrum  .ui-h2,.u-resetSpectrum  .ui-h3,.u-resetSpectrum  .ui-h4,.u-resetSpectrum  .ui-brand1,.u-resetSpectrum  .ui-brand2,.u-resetSpectrum  .ui-captionStrong {color: rgba(0, 0, 0, 0.8) !important; fill: rgba(0, 0, 0, 0.8) !important;}
.u-resetSpectrum  .ui-body,.u-resetSpectrum  .ui-caps {color: rgba(0, 0, 0, 0.6) !important; fill: rgba(0, 0, 0, 0.6) !important;}
.u-resetSpectrum  .ui-summary,.u-resetSpectrum  .ui-caption {color: rgba(0, 0, 0, 0.2980392156862745) !important; fill: rgba(0, 0, 0, 0.2980392156862745) !important;}
.u-resetSpectrum .u-accentColor--borderLight {border-color: rgba(2, 184, 117, 1) !important;}
.u-resetSpectrum .u-accentColor--borderNormal {border-color: rgba(2, 184, 117, 1) !important;}
.u-resetSpectrum .u-accentColor--borderDark {border-color: rgba(0, 171, 107, 1) !important;}
.u-resetSpectrum .u-accentColor--iconLight .svgIcon,.u-resetSpectrum .u-accentColor--iconLight.svgIcon {fill: rgba(2, 184, 117, 1) !important;}
.u-resetSpectrum .u-accentColor--iconNormal .svgIcon,.u-resetSpectrum .u-accentColor--iconNormal.svgIcon {fill: rgba(0, 171, 107, 1) !important;}
.u-resetSpectrum .u-accentColor--iconDark .svgIcon,.u-resetSpectrum .u-accentColor--iconDark.svgIcon {fill: rgba(28, 153, 99, 1) !important;}
.u-resetSpectrum .u-accentColor--textNormal {color: rgba(0, 171, 107, 1) !important;}
.u-resetSpectrum .u-accentColor--hoverTextNormal:hover {color: rgba(0, 171, 107, 1) !important;}
.u-resetSpectrum .u-accentColor--textNormal.u-accentColor--textDarken:hover {color: rgba(28, 153, 99, 1) !important;}
.u-resetSpectrum .u-accentColor--textDark {color: rgba(28, 153, 99, 1) !important;}
.u-resetSpectrum .u-accentColor--backgroundLight {background-color: rgba(2, 184, 117, 1) !important;}
.u-resetSpectrum .u-accentColor--backgroundNormal {background-color: rgba(0, 171, 107, 1) !important;}
.u-resetSpectrum .u-accentColor--backgroundDark {background-color: rgba(28, 153, 99, 1) !important;}
.u-resetSpectrum .u-accentColor--buttonDark {border-color: rgba(0, 171, 107, 1) !important; color: rgba(28, 153, 99, 1) !important;}
.u-resetSpectrum .u-accentColor--buttonDark:hover {border-color: rgba(28, 153, 99, 1) !important;}
.u-resetSpectrum .u-accentColor--buttonDark .icon:before,.u-resetSpectrum .u-accentColor--buttonDark .svgIcon{color: rgba(28, 153, 99, 1) !important; fill: rgba(28, 153, 99, 1) !important;}
.u-resetSpectrum .u-accentColor--buttonNormal:not(.clapButton--largePill) {border-color: rgba(2, 184, 117, 1) !important; color: rgba(0, 171, 107, 1) !important;}
.u-resetSpectrum .u-accentColor--buttonNormal:hover {border-color: rgba(0, 171, 107, 1) !important;}
.u-resetSpectrum .u-accentColor--buttonNormal .icon:before,.u-resetSpectrum .u-accentColor--buttonNormal .svgIcon{color: rgba(0, 171, 107, 1) !important; fill: rgba(0, 171, 107, 1) !important;}
.u-resetSpectrum .u-accentColor--buttonNormal.button--filled .icon:before,.u-resetSpectrum .u-accentColor--buttonNormal.button--filled .svgIcon{color: rgba(255, 255, 255, 1) !important; fill: rgba(255, 255, 255, 1) !important;}
.u-resetSpectrum .u-accentColor--buttonDark.button--filled,.u-resetSpectrum .u-accentColor--buttonDark.button--withChrome.is-active,.u-resetSpectrum .u-accentColor--fillWhenActive.is-active {background-color: rgba(28, 153, 99, 1) !important; border-color: rgba(28, 153, 99, 1) !important; color: rgba(255, 255, 255, 1) !important; fill: rgba(255, 255, 255, 1) !important;}
.u-resetSpectrum .u-accentColor--buttonNormal.button--filled:not(.clapButton--largePill),.u-resetSpectrum .u-accentColor--buttonNormal.button--withChrome.is-active:not(.clapButton--largePill) {background-color: rgba(0, 171, 107, 1) !important; border-color: rgba(0, 171, 107, 1) !important; color: rgba(255, 255, 255, 1) !important; fill: rgba(255, 255, 255, 1) !important;}
.u-resetSpectrum .postArticle.is-withAccentColors .markup--user,.u-resetSpectrum .postArticle.is-withAccentColors .markup--query {color: rgba(0, 171, 107, 1) !important;}</style></div></div></div><div class="loadingBar"></div><script>// <![CDATA[
window["obvInit"] = function (opt_embedded) {window["obvInit"]["embedded"] = opt_embedded; window["obvInit"]["ready"] = true;}
// ]]></script><script>// <![CDATA[
var GLOBALS = {"audioUrl":"https://d1fcbxp97j4nb2.cloudfront.net","baseUrl":"https://towardsdatascience.com","buildLabel":"32627-551b284","currentUser":{"userId":"lo_Pde0GEfT2sEl","isVerified":false,"subscriberEmail":"","hasPastMemberships":false,"isEnrolledInHightower":false,"isEligibleForHightower":false,"hightowerLastLockedAt":0},"currentUserHasUnverifiedEmail":false,"isAuthenticated":false,"isCurrentUserVerified":false,"mediumTwitterScreenName":"medium","miroUrl":"https://cdn-images-1.medium.com","moduleUrls":{"base":"https://cdn-static-1.medium.com/_/fp/gen-js/main-base.bundle.nrW6tpdILEZhePtrJ0pHGg.js","common-async":"https://cdn-static-1.medium.com/_/fp/gen-js/main-common-async.bundle.SE4UC1BeB-mzSxMKcRmBKA.js","hightower":"https://cdn-static-1.medium.com/_/fp/gen-js/main-hightower.bundle.JOPsOLtp5rIR4WlyzBhwWA.js","home-screens":"https://cdn-static-1.medium.com/_/fp/gen-js/main-home-screens.bundle.K8q4FVZMKXlmIVIdvNgdog.js","misc-screens":"https://cdn-static-1.medium.com/_/fp/gen-js/main-misc-screens.bundle.NSu8pWy8NdTuVsy6CqZILA.js","notes":"https://cdn-static-1.medium.com/_/fp/gen-js/main-notes.bundle.GzdYiMH2a3xVqHpRElapCQ.js","payments":"https://cdn-static-1.medium.com/_/fp/gen-js/main-payments.bundle.-U74QgqraY1pCu6laDfjYw.js","posters":"https://cdn-static-1.medium.com/_/fp/gen-js/main-posters.bundle.KHTskmImBIeDos-qouN-FA.js","power-readers":"https://cdn-static-1.medium.com/_/fp/gen-js/main-power-readers.bundle.OHJaguz-DSAMJr__FgWU1g.js","pubs":"https://cdn-static-1.medium.com/_/fp/gen-js/main-pubs.bundle.Rm4TTkV-WxRVhkqwQ6YXqg.js","stats":"https://cdn-static-1.medium.com/_/fp/gen-js/main-stats.bundle.m8bc51OqgsxgLQXpF1lVLw.js"},"previewConfig":{"weightThreshold":1,"weightImageParagraph":0.51,"weightIframeParagraph":0.8,"weightTextParagraph":0.08,"weightEmptyParagraph":0,"weightP":0.003,"weightH":0.005,"weightBq":0.003,"minPTextLength":60,"truncateBoundaryChars":20,"detectTitle":true,"detectTitleLevThreshold":0.15},"productName":"Medium","supportsEdit":false,"termsUrl":"//medium.com/policy/9db0094a1e0f","textshotHost":"textshot.medium.com","transactionId":"1518608205014:8e23045eae5c","useragent":{"browser":"python requests","family":"","os":"","version":2.1,"supportsDesktopEdit":false,"supportsInteract":false,"supportsView":true,"isMobile":false,"isTablet":false,"isNative":false,"supportsFileAPI":false,"isTier1":false,"clientVersion":"","unknownParagraphsBad":false,"clientChannel":"","supportsRealScrollEvents":false,"supportsVhUnits":false,"ruinsViewportSections":false,"supportsHtml5Video":false,"supportsMagicUnderlines":false,"isWebView":false,"isFacebookWebView":false,"supportsProgressiveMedia":false,"supportsPromotedPosts":true,"isBot":false,"isNativeIphone":false,"supportsCssVariables":false,"supportsVideoSections":true,"emojiSupportLevel":1,"isSearchBot":false,"supportsScrollableMetabar":false},"variants":{"allow_access":true,"allow_signup":true,"allow_test_auth":"disallow","signin_services":"twitter,facebook,google,email,google-fastidv","signup_services":"twitter,facebook,google,email,google-fastidv","android_rating_prompt_recommend_threshold":5,"google_sign_in_android":true,"reengagement_notification_duration":3,"browsable_stream_config_bucket":"universal-nav-bar","enable_series_creation":true,"enable_your_series_pages":true,"enable_productionized_series":true,"enable_dedicated_series_tab_api_ios":true,"enable_clap_milestone_notifications":true,"enable_series_stats_page":true,"enable_post_import":true,"enable_sponsored_post_labelling":true,"enable_logged_in_follow_on_collection_post":true,"enable_export_members":true,"enable_series_card_background_creation":true,"available_monthly_plan":"60e220181034","available_annual_plan":"2c754bcc2995","enable_sms":true,"is_not_medium_subscriber":true,"disable_followed_tag_fan_out":true,"enable_emoji_in_editor":true,"enable_glyph":true,"glyph_font_set":"m2","enable_branding":true,"enable_branding_fonts":true,"enable_branding_buttons":true,"enable_sequence_carousel":true,"enable_multirecommends":true,"enable_view_new_collection_writers_manager":true,"enable_user_post_metering":true,"max_premium_content_per_user_under_metering":3,"tag_intercom_user_on_metering_count":3,"enable_topic_writer_onboarding":true,"enable_algolia_search_reporting":true,"enable_strong_graph_chp_reorder":true,"enable_unsplash_images":true,"enable_top_stories_for_you":true,"enable_ios_member_post_labeling":true,"enable_featured_hero":true,"enable_li_search_collection":true,"enable_revamped_nav_bar":true,"enable_gosocial_aurora_shadow_reads":true,"enable_audio_playlists":true,"enable_homepage_remodel":true,"enable_platform_934_loading":true,"enable_standalone_profile_edit_page":true,"enable_standalone_user_follow_pages":true,"enable_post_footer_copy":true,"enable_february_awareness_email_campaign":true,"app_download_email_template":"routine","enable_bloomd_double_write":true,"enable_bloomd_sharding":true,"enable_hack_series_web":true,"disable_digest_deep_social_provider":true,"enable_cf_in_digest":true,"enable_logged_in_payment_flow_membership_lp":true,"enable_paypal_option":true,"enable_digest_presentation_data_collection":true,"enable_new_source_for_new_from_your_network":true,"enable_digest_ui_revamp":true,"enable_marketing_emails":true},"xsrfToken":"","iosAppId":"828256236","supportEmail":"yourfriends@medium.com","fp":{"/icons/monogram-mask.svg":"https://cdn-static-1.medium.com/_/fp/icons/monogram-mask.KPLCSFEZviQN0jQ7veN2RQ.svg","/icons/favicon-dev-editor.ico":"https://cdn-static-1.medium.com/_/fp/icons/favicon-dev-editor.YKKRxBO8EMvIqhyCwIiJeQ.ico","/icons/favicon-hatch-editor.ico":"https://cdn-static-1.medium.com/_/fp/icons/favicon-hatch-editor.BuEyHIqlyh2s_XEk4Rl32Q.ico","/icons/favicon-medium-editor.ico":"https://cdn-static-1.medium.com/_/fp/icons/favicon-medium-editor.PiakrZWB7Yb80quUVQWM6g.ico"},"authBaseUrl":"https://medium.com","imageUploadSizeMb":25,"isAuthDomainRequest":false,"domainCollectionSlug":"towards-data-science","algoliaApiEndpoint":"https://MQ57UUUQZ2-dsn.algolia.net","algoliaAppId":"MQ57UUUQZ2","algoliaSearchOnlyApiKey":"394474ced050e3911ae2249ecc774921","iosAppStoreUrl":"https://itunes.apple.com/app/medium-everyones-stories/id828256236?pt=698524&mt=8","iosAppLinkBaseUrl":"medium:","algoliaIndexPrefix":"medium_","androidPlayStoreUrl":"https://play.google.com/store/apps/details?id=com.medium.reader","googleClientId":"216296035834-k1k6qe060s2tp2a2jam4ljdcms00sttg.apps.googleusercontent.com","androidPackage":"com.medium.reader","androidPlayStoreMarketScheme":"market://details?id=com.medium.reader","googleAuthUri":"https://accounts.google.com/o/oauth2/auth","androidScheme":"medium","layoutData":{"useDynamicScripts":false,"googleAnalyticsTrackingCode":"UA-24232453-2","jsShivUrl":"https://cdn-static-1.medium.com/_/fp/js/shiv.RI2ePTZ5gFmMgLzG5bEVAA.js","useDynamicCss":false,"faviconUrl":"https://cdn-static-1.medium.com/_/fp/icons/favicon-rebrand-medium.3Y6xpZ-0FSdWDnPM3hSBIA.ico","faviconImageId":"1*8I-HPL0bfoIzGied-dzOvA.png","fontSets":[{"id":8,"url":"https://glyph.medium.com/css/e/sr/latin/e/ssr/latin/e/ssb/latin/m2.css"},{"id":9,"url":"https://glyph.medium.com/css/mkt.css"},{"id":10,"url":"https://glyph.medium.com/css/elv8.css"}],"editorFaviconUrl":"https://cdn-static-1.medium.com/_/fp/icons/favicon-rebrand-medium-editor.3Y6xpZ-0FSdWDnPM3hSBIA.ico","glyphUrl":"https://glyph.medium.com"},"authBaseUrlRev":"moc.muidem//:sptth","isDnt":false,"stripePublishableKey":"pk_live_7FReX44VnNIInZwrIIx6ghjl","archiveUploadSizeMb":100,"paymentData":{"currencies":{"1":{"label":"US Dollar","external":"usd"}},"countries":{"1":{"label":"United States of America","external":"US"}},"accountTypes":{"1":{"label":"Individual","external":"individual"},"2":{"label":"Company","external":"company"}}},"previewConfig2":{"weightThreshold":1,"weightImageParagraph":0.05,"raiseImage":true,"enforceHeaderHierarchy":true,"isImageInsetRight":true},"isAmp":false,"iosScheme":"medium","isSwBoot":false,"lightstep":{"accessToken":"ce5be895bef60919541332990ac9fef2","carrier":"{\"ot-tracer-spanid\":\"192601bb7c19b658\",\"ot-tracer-traceid\":\"38fd699651251b4f\",\"ot-tracer-sampled\":\"true\"}","host":"collector-medium.lightstep.com"},"facebook":{"key":"542599432471018","namespace":"medium-com","scope":{"default":["public_profile","email","user_friends"],"connect":["public_profile","email","user_friends"],"login":["public_profile","email","user_friends"],"share":["public_profile","email","user_friends","publish_actions"]}},"mailingListArchiveUploadSizeMb":2,"editorsPicksTopicId":"3985d2a191c5","popularOnMediumTopicId":"9d34e48ecf94","memberContentTopicId":"13d7efd82fb2","audioContentTopicId":"3792abbd134","brandedSequenceId":"7d337ddf1941","isDoNotAuth":false,"goldfinchUrl":"https://goldfinch.medium.com","buggle":{"url":"https://buggle.medium.com","videoUrl":"https://cdn-videos-1.medium.com","audioUrl":"https://cdn-audio-1.medium.com"},"referrerType":5,"isMeteredOut":false,"meterConfig":{"maxUnlockCount":3,"windowLength":"MONTHLY"},"partnerProgramEmail":"partnerprogram@medium.com","userResearchPrompts":[{"promptId":"lo_post_page_4","type":0,"url":"www.calendly.com"},{"promptId":"lo_home_page","type":1,"url":"www.calendly.com"},{"promptId":"lo_profile_page","type":2,"url":"www.calendly.com"}],"recaptchaKey":"6LdAokEUAAAAAC7seICd4vtC8chDb3jIXDQulyUJ","paypalClientMode":"production","signinWallCustomDomainCollectionIds":["3a8144eabfe3"]}
// ]]></script><script charset="UTF-8" src="https://cdn-static-1.medium.com/_/fp/gen-js/main-base.bundle.nrW6tpdILEZhePtrJ0pHGg.js" async></script><script>// <![CDATA[
window["obvInit"]({"value":{"id":"3275042fbd8d","versionId":"5e882bdf7b03","creatorId":"44ee44e12515","creator":{"userId":"44ee44e12515","name":"Rafael Aldon","username":"raldon","createdAt":1491556308897,"lastPostCreatedAt":1505710391517,"imageId":"1*xyfTiylyHHiLyxJTJQy8AQ.png","backgroundImageId":"","bio":"Early-Stage Venture Capital in Asia | Tech Investor | Startup Advisor | FinTech & Blockchain Enthusiast | Formula 1 Nut","twitterScreenName":"","socialStats":{"userId":"44ee44e12515","usersFollowedCount":34,"usersFollowedByCount":11,"type":"SocialStats"},"social":{"userId":"lo_Pde0GEfT2sEl","targetUserId":"44ee44e12515","type":"Social"},"facebookAccountId":"","allowNotes":1,"isNsfw":false,"type":"User"},"homeCollection":{"id":"7f60cf5620c9","name":"Towards Data Science","slug":"towards-data-science","tags":["DATA SCIENCE","MACHINE LEARNING","ARTIFICIAL INTELLIGENCE","BIG DATA","ANALYTICS"],"creatorId":"895063a310f4","description":"Sharing concepts, ideas, and codes.","shortDescription":"Sharing concepts, ideas, and codes.","image":{"imageId":"1*F0LADxTtsKOgmPa-_7iUEQ.jpeg","filter":"","backgroundSize":"","originalWidth":1275,"originalHeight":1275,"strategy":"resample","height":0,"width":0},"metadata":{"followerCount":53890,"activeAt":1518560422160},"virtuals":{"permissions":{"canPublish":false,"canPublishAll":false,"canRepublish":false,"canRemove":false,"canManageAll":false,"canSubmit":false,"canEditPosts":false,"canAddWriters":false,"canViewStats":false,"canSendNewsletter":false,"canViewLockedPosts":false,"canViewCloaked":false,"canEditOwnPosts":false,"canBeAssignedAuthor":false,"canEnrollInHightower":false,"canLockPostsForMediumMembers":false},"isSubscribed":false,"isNewsletterSubscribed":false,"memberOfMembershipPlanId":"","isEnrolledInHightower":false,"isEligibleForHightower":false},"logo":{"imageId":"","filter":"","backgroundSize":"","originalWidth":0,"originalHeight":0,"strategy":"resample","height":0,"width":0},"twitterUsername":"TDataScience","facebookPageName":"towardsdatascience","publicEmail":"publication@towardsdatascience.com","collectionMastheadId":"8b6aceffde6","domain":"towardsdatascience.com","sections":[{"type":2,"collectionHeaderMetadata":{"title":"Towards Data Science","description":"Sharing concepts, ideas, and codes","backgroundImage":{},"logoImage":{},"alignment":2,"layout":5}},{"type":1,"postListMetadata":{"source":4,"layout":2,"number":1,"postIds":[],"tagSlug":"Towards Data Science"}},{"type":1,"postListMetadata":{"source":1,"layout":4,"number":6,"postIds":[],"sectionHeader":"Latest"}},{"type":1,"postListMetadata":{"source":3,"layout":4,"number":2,"postIds":["ee524ca64416","e2be7fb8d038"],"sectionHeader":"Our letters"}},{"type":3,"promoMetadata":{"sectionHeader":"","promoId":"dbabc89840b7"}},{"type":1,"postListMetadata":{"source":2,"layout":7,"number":7,"postIds":[],"sectionHeader":"Trending"}},{"type":3,"promoMetadata":{"sectionHeader":"","promoId":"69b26f0f1e35"}},{"type":1,"postListMetadata":{"source":4,"layout":4,"number":9,"postIds":[],"tagSlug":"Towards Data Science","sectionHeader":"Editors' Picks"}},{"type":3,"promoMetadata":{"sectionHeader":"","promoId":"8b04cd40f0c8"}},{"type":1,"postListMetadata":{"source":4,"layout":5,"number":3,"postIds":[],"tagSlug":"Towards Data Science","sectionHeader":"Last chance to read"}}],"tintColor":"#FF355876","lightText":true,"favicon":{"imageId":"1*F0LADxTtsKOgmPa-_7iUEQ.jpeg","filter":"","backgroundSize":"","originalWidth":1275,"originalHeight":1275,"strategy":"resample","height":0,"width":0},"colorPalette":{"defaultBackgroundSpectrum":{"colorPoints":[{"color":"#FF668AAA","point":0},{"color":"#FF61809D","point":0.1},{"color":"#FF5A7690","point":0.2},{"color":"#FF546C83","point":0.3},{"color":"#FF4D6275","point":0.4},{"color":"#FF455768","point":0.5},{"color":"#FF3D4C5A","point":0.6},{"color":"#FF34414C","point":0.7},{"color":"#FF2B353E","point":0.8},{"color":"#FF21282F","point":0.9},{"color":"#FF161B1F","point":1}],"backgroundColor":"#FFFFFFFF"},"tintBackgroundSpectrum":{"colorPoints":[{"color":"#FF355876","point":0},{"color":"#FF4D6C88","point":0.1},{"color":"#FF637F99","point":0.2},{"color":"#FF7791A8","point":0.3},{"color":"#FF8CA2B7","point":0.4},{"color":"#FF9FB3C6","point":0.5},{"color":"#FFB2C3D4","point":0.6},{"color":"#FFC5D2E1","point":0.7},{"color":"#FFD7E2EE","point":0.8},{"color":"#FFE9F1FA","point":0.9},{"color":"#FFFBFFFF","point":1}],"backgroundColor":"#FF355876"},"highlightSpectrum":{"colorPoints":[{"color":"#FFEDF4FC","point":0},{"color":"#FFE9F2FD","point":0.1},{"color":"#FFE6F1FD","point":0.2},{"color":"#FFE2EFFD","point":0.3},{"color":"#FFDFEEFD","point":0.4},{"color":"#FFDBECFE","point":0.5},{"color":"#FFD7EBFE","point":0.6},{"color":"#FFD4E9FE","point":0.7},{"color":"#FFD0E7FF","point":0.8},{"color":"#FFCCE6FF","point":0.9},{"color":"#FFC8E4FF","point":1}],"backgroundColor":"#FFFFFFFF"}},"navItems":[{"type":4,"title":"Data Science","url":"https://towardsdatascience.com/data-science/home","topicId":"cf416843aadc","source":"topicId"},{"type":4,"title":"Machine Learning","url":"https://towardsdatascience.com/machine-learning/home","topicId":"a5c9b2f1cb6b","source":"topicId"},{"type":4,"title":"Programming","url":"https://towardsdatascience.com/programming/home","topicId":"41533a1dc73c","source":"topicId"},{"type":4,"title":"Visualization","url":"https://towardsdatascience.com/data-visualization/home","topicId":"825e6cb8b9ce","source":"topicId"},{"type":4,"title":"Letters","url":"https://towardsdatascience.com/newsletters/home","topicId":"83f438f06a8c","source":"topicId"},{"type":4,"title":"Contribute","url":"https://towardsdatascience.com/contribute/home","topicId":"6ae0c8697d8c","source":"topicId"},{"type":3,"title":"Become a Patreon","url":"https://www.patreon.com/towardsdatascience/"}],"colorBehavior":2,"instantArticlesState":0,"acceleratedMobilePagesState":0,"googleAnalyticsId":"UA-19707169-24","ampLogo":{"imageId":"","filter":"","backgroundSize":"","originalWidth":0,"originalHeight":0,"strategy":"resample","height":0,"width":0},"header":{"title":"Towards Data Science","description":"Sharing concepts, ideas, and codes","backgroundImage":{},"logoImage":{},"alignment":2,"layout":5},"paidForDomainAt":1509037374118,"type":"Collection"},"homeCollectionId":"7f60cf5620c9","title":"Hurricane Harvey InsurTech Case Study; visual intelligence is transforming claim response times.","detectedLanguage":"en","latestVersion":"5e882bdf7b03","latestPublishedVersion":"5e882bdf7b03","hasUnpublishedEdits":false,"latestRev":179,"createdAt":1505710391517,"updatedAt":1516854422206,"acceptedAt":0,"firstPublishedAt":1505870971504,"latestPublishedAt":1506561617694,"vote":false,"experimentalCss":"","displayAuthor":"","content":{"subtitle":"Storms of unprecedented power have lashed the United States and the Caribbean over the past few weeks, leaving a trail of devastation…","bodyModel":{"paragraphs":[{"name":"1f4d","type":3,"text":"Hurricane Harvey InsurTech Case Study; visual intelligence is transforming claim response times.","markups":[]},{"name":"77db","type":4,"text":"Hurricane Harvey as seen from the International Space Station","markups":[],"layout":1,"metadata":{"id":"1*lSrjjYyG8X2ND8hFmjBtAA.png","originalWidth":940,"originalHeight":627,"isFeatured":true}},{"name":"70c4","type":1,"text":"Storms of unprecedented power have lashed the United States and the Caribbean over the past few weeks, leaving a trail of devastation estimated in the tens of billions of dollars.","markups":[]},{"name":"5e62","type":1,"text":"The US alone has experienced 212 natural disasters since 1980 with the overall costs totalling $1.2tn, according to the National Oceanic and Atmospheric Association (NOAA).","markups":[]},{"name":"9e5b","type":1,"text":"As a venture investor interested in FinTech, I get sight of quite a lot of innovative InsurTech Start-up’s hoping to be the next big thing in insurance. Barely any of these businesses are focused on improving claims management. Why is that?","markups":[]},{"name":"6381","type":1,"text":"Perhaps Claims are considered the least ‘sexy’ aspect of the insurance industry, a necessary evil if you like. Good Insurers understand the claims experience is one of the most important parts of insurance. Insurance, after all, is a promise to make good your losses in case of an accident.","markups":[]},{"name":"0c81","type":1,"text":"Natural disasters are brutal. They leave people vulnerable and exposed, and a speedy resolution by the insurer is crucial to the customer experience, encourages customer retention and also saves the insurer time and money.","markups":[]},{"name":"dbad","type":1,"text":"That’s an easy thing to say, but dynamically responding to claims after events of the magnitude of Hurricanes Harvey and Irma is no mean feat. It’s often impossible for people to access the areas for quite some time, by which point storm surges have subsided, and claims can be harder to assess.","markups":[]},{"name":"b164","type":1,"text":"One company actively addressing this challenge for insurers is Geospatial Insight. VenturesOne announced a growth equity investment in them recently and I was with their team in the UK. They had just delivered incredibly detailed visual intelligence on Hurricane Harvey to enable Insurers and their corporate clients understand the situation at ground level and respond swiftly to claims.","markups":[{"type":3,"start":63,"end":81,"href":"https://www.geospatial-insight.com/","title":"","rel":"","anchorType":0},{"type":3,"start":95,"end":139,"href":"http://venturesone.com/venturesone-fuels-geospatial-insight/","title":"","rel":"","anchorType":0}]},{"name":"669e","type":1,"text":"There are three main challenges that an insurer can address by adopting visual intelligence services after a natural disaster:","markups":[]},{"name":"ad83","type":1,"text":"1) The approximate total claim size likely as a result of the event.","markups":[]},{"name":"4c60","type":1,"text":"2) An accurate map of the area impacted by the event to prevent fraudulent claims.","markups":[]},{"name":"3134","type":1,"text":"3) That the proximate cause of the claim is directly related to the event.","markups":[]},{"name":"959f","type":1,"text":"There is a lot of hype around the possibilities of advancing techs like machine learning, big data and drones etc, but I see less in the way of tangible examples of how they can be combined to deliver benefits right now, so here is a real-life example.","markups":[]},{"name":"ed9c","type":3,"text":"Hurricane Harvey Case Study","markups":[{"type":1,"start":0,"end":27}]},{"name":"c7af","type":1,"text":"On August 25th, category 4 Hurricane Harvey makes Landfall near Rockport Texas.","markups":[]},{"name":"f2d1","type":4,"text":"","markups":[],"layout":1,"metadata":{"id":"0*RE_j6FoGu5zb2mXY.png","originalWidth":815,"originalHeight":459}},{"name":"6e4e","type":1,"text":"Harvey causes catastrophic flooding, with 50+ inches of rainfall in some areas (a record from a tropical cyclone in the USA). Harvey covers over 20,000 square miles in 72 hours, displacing 30,000 people.","markups":[]},{"name":"091e","type":1,"text":"Situational Analysis","markups":[{"type":1,"start":0,"end":20}]},{"name":"4dee","type":1,"text":"The first step was to make an initial assessment of the affected area and a rapid review of expected Insurance customers’ requirements. The densely populated residential and commercial area of greater Houston was set.","markups":[]},{"name":"3081","type":4,"text":"","markups":[],"layout":1,"metadata":{"id":"0*9zceP3dvu_sbUJsw.png","originalWidth":628,"originalHeight":353}},{"name":"3f5c","type":1,"text":"Big Data Collection, Processing & Analytics","markups":[{"type":1,"start":0,"end":43}]},{"name":"312b","type":1,"text":"Although Harvey made landfall on Friday the weather event continued with torrential rainfall throughout the days that followed. By weds 30th it is estimated that a mind-boggling 24.5 trillion gallons of rainwater was dumped from the Gulf of Mexico across Houston and Southern Texas.","markups":[]},{"name":"2307","type":4,"text":"","markups":[],"layout":1,"metadata":{"id":"0*ZDwHwza6N7e4J31e.png","originalWidth":515,"originalHeight":693}},{"name":"0673","type":1,"text":"To get the most comprehensive understanding possible a diverse variety of data sets were collated including terrain data, satellite imagery, drone footage from social media scrapes and independent commissioned light aircraft with specialist high-resolution camera imagery.","markups":[]},{"name":"d69b","type":1,"text":"The team used the data collected from aerial and social to calibrate the threshold used to generate the sentinel footprint. Geospatial Insight then use proprietary algorithms to cluster the areas detected as water into flooded areas","markups":[]},{"name":"8011","type":4,"text":"","markups":[],"layout":1,"metadata":{"id":"0*cikAKImGstvJtxmH.png","originalWidth":946,"originalHeight":582}},{"name":"9c18","type":1,"text":"To understand the likely impact of Harvey on homes and commercial buildings the multiple data sets were combined to gain insight into flood extents. The colour coded image below shows different data sources.","markups":[]},{"name":"341d","type":4,"text":"","markups":[],"layout":1,"metadata":{"id":"0*lVYEn3LbTs4tsPT8.png","originalWidth":908,"originalHeight":608}},{"name":"e293","type":1,"text":"The blue is derived from the National Oceanic and Atmosphere Association (NOAA) imagery and an aerial survey using a Midas oblique camera system.","markups":[]},{"name":"8c27","type":1,"text":"The red is Sentinel 1 RADAR satellite that can penetrate cloud cover to identify areas of standing water.","markups":[]},{"name":"beaa","type":1,"text":"The small pockets of yellow are derived from Geospatial Insight’s social media scraping tool to find photos and videos of the event which can then be mapped to build the extents from video evidence. Typically, the team use their global network of licensed UAV operators that work to agreed SLA’s to map flood areas with drones, however, drones were banned over Houston during this time frame due to emergency services using the airspace for rescues etc.","markups":[]},{"name":"f47d","type":1,"text":"Footage like the example below were identified and then the flight path and flood extents expertly mapped.","markups":[]},{"name":"502e","type":11,"text":"","markups":[],"layout":1,"iframe":{"mediaResourceId":"b644432f2314eb1fb10f041164f8c996","iframeWidth":854,"iframeHeight":480,"thumbnailUrl":"https://i.embed.ly/1/image?url=https%3A%2F%2Fi.ytimg.com%2Fvi%2FbjQS5q2l41Q%2Fhqdefault.jpg&key=a19fcc184b9711e1b4764040d3dc5c07"}},{"name":"62fa","type":1,"text":"Why was the flooding so severe?","markups":[{"type":1,"start":0,"end":31}]},{"name":"5641","type":1,"text":"You can clearly see the two large blue reservoirs on the west side of Houston, Addicks to the North of Interstate 10, and Barker to the South. They are designed to protect Houston from flooding and both dams feed into the Buffalo Bayou. The reservoirs are surrounded by parks and residential areas and by Monday evening water levels had already reached record levels, measuring 105 feet at Addicks (North) and 99 feet at Barker (South).","markups":[]},{"name":"c1a9","type":4,"text":"","markups":[],"layout":1,"metadata":{"id":"0*8CbPxaZpkrghMTG0.png","originalWidth":684,"originalHeight":560}},{"name":"09a5","type":1,"text":"Local officials hoped to prevent a spill-over by slowly releasing water from both the Addicks and Barker dams on Tues and Weds. However, the storm surge was so great that the engineers had to release water through the dam gates much earlier than expected or risk it spilling over and causing further damage to homes. A warning was given to homes to evacuate in the early hours of Monday morning, however, the decision was made to release the pressure late Sunday night and many residents became stranded in the resulting swell.","markups":[]},{"name":"a314","type":4,"text":"","markups":[],"layout":1,"metadata":{"id":"0*4Hh1k_jjaZo7DMLA.png","originalWidth":425,"originalHeight":395}},{"name":"c4fd","type":1,"text":"Accelerating Claims with Visual Intelligence","markups":[{"type":1,"start":0,"end":44}]},{"name":"e2df","type":1,"text":"In order to provide the intelligence required to rapidly address insurance claims, the Geospatial Insight team needed to first make sense of huge amounts of unstructured data.","markups":[]},{"name":"c4de","type":1,"text":"Not only the diverse image sources but also client information for insurance customers and corporate responsibility data like home addresses of employees to map the affected customers and staff.","markups":[]},{"name":"2994","type":1,"text":"This data was quickly mapped and the multiple image sources applied as layers to allow corporate clients to access and make sense of the information via Geospatial Insights dedicated customer portal.","markups":[]},{"name":"5068","type":4,"text":"","markups":[],"layout":1,"metadata":{"id":"0*5fjLzerjd7MQ9nsD.png","originalWidth":939,"originalHeight":438}},{"name":"2213","type":1,"text":"The image above shows the client portal with claim location points identified in yellow.","markups":[]},{"name":"fb07","type":1,"text":"High-resolution satellite images can be a good indicator however they are top-down view so much harder to get an accurate perspective on the level of damage on a property. Images at an oblique angle were needed to help quantify this over a vast area and thus Geospatial Insight commissioned a light aircraft equipped with a Midas 5 camera to map the most affected region for high-resolution imagery.","markups":[]},{"name":"a34e","type":1,"text":"The visualisation below shows how this camera is able to capture oblique angles in four directions simultaneously (along with an overhead view).","markups":[]},{"name":"7608","type":4,"text":"","markups":[],"layout":1,"metadata":{"id":"0*Uzhvf31E3eFECgQW.png","originalWidth":609,"originalHeight":941}},{"name":"a90e","type":1,"text":"Using this technique, huge areas could be imaged in high resolution and then mapped to provide oblique angled images in North, South, East and West orientations for accurate analysis of identified claim locations.","markups":[]},{"name":"58ae","type":4,"text":"","markups":[],"layout":1,"metadata":{"id":"0*q3zSh_dGS5fxievW.png","originalWidth":778,"originalHeight":529}},{"name":"fd83","type":1,"text":"With this resolution and volume of data, the Geospatial Insight team could identify the evidence of flooding such as remaining water, sediment and waste outside houses even after the flooding has drained away. Below is an example image showing home furnishings being disposed of. You can clearly see the raised swimming pools that remained clean and blue compared to those that were ruined by the storm surge.","markups":[]},{"name":"4e9f","type":4,"text":"","markups":[],"layout":1,"metadata":{"id":"0*LSgSGuCXfYw57847.png","originalWidth":815,"originalHeight":546}},{"name":"1d17","type":1,"text":"Rebuilding Lives After Disaster","markups":[{"type":1,"start":0,"end":31}]},{"name":"bf62","type":1,"text":"Sadly, it seems many residents of Houston were uninsured and face rebuilding their lives without any form of insurance pay-out. For those with cover, getting access to funds quickly will make all the difference.","markups":[]},{"name":"71a4","type":1,"text":"By embracing the kind of technology deployed above, insurers can make a meaningful difference in helping residents, businesses and communities get back on their feet as quickly as possible.","markups":[]},{"name":"7d13","type":1,"text":"— — — — — — — —","markups":[]},{"name":"0549","type":1,"text":"For more info on the company you can visit www.geospatial-insight.com or just message me and I would be happy to afford you an introduction to the team.","markups":[{"type":3,"start":43,"end":69,"href":"http://www.geospatial-insight.com/","title":"","rel":"nofollow noopener","anchorType":0}]}],"sections":[{"name":"c9db","startIndex":0}]},"postDisplay":{"coverless":true}},"virtuals":{"statusForCollection":"APPROVED","allowNotes":true,"previewImage":{"imageId":"1*lSrjjYyG8X2ND8hFmjBtAA.png","filter":"","backgroundSize":"","originalWidth":940,"originalHeight":627,"strategy":"resample","height":0,"width":0},"wordCount":1362,"imageCount":12,"readingTime":6.489622641509435,"subtitle":"Storms of unprecedented power have lashed the United States and the Caribbean over the past few weeks, leaving a trail of devastation…","publishedInCount":1,"usersBySocialRecommends":[],"recommends":6,"socialRecommends":[],"isBookmarked":false,"tags":[{"slug":"hurricane-harvey","name":"Hurricane Harvey","postCount":1185,"virtuals":{"isFollowing":false},"metadata":{"followerCount":3,"postCount":1185,"coverImage":{"id":"1*JCfYtXskAZVpCf5AVlF3yQ.png","originalWidth":1528,"originalHeight":1000,"isFeatured":true}},"type":"Tag"},{"slug":"insurance","name":"Insurance","postCount":8988,"virtuals":{"isFollowing":false},"metadata":{"followerCount":377,"postCount":8988,"coverImage":{"id":"1*QnMN0vvd5ZEk6kxgN_9yZg.png","originalWidth":585,"originalHeight":839}},"type":"Tag"},{"slug":"machine-learning","name":"Machine Learning","postCount":28212,"virtuals":{"isFollowing":false},"metadata":{"followerCount":23776,"postCount":28212,"coverImage":{"id":"1*DlGlK5i8Q44MdIWtKNp6ug.jpeg","originalWidth":500,"originalHeight":333}},"type":"Tag"},{"slug":"big-data","name":"Big Data","postCount":17524,"virtuals":{"isFollowing":false},"metadata":{"followerCount":9248,"postCount":17524,"coverImage":{"id":"1*7n0kA1YU9KU7t69MyyWE2A.jpeg","originalWidth":5184,"originalHeight":3456,"isFeatured":true}},"type":"Tag"},{"slug":"towards-data-science","name":"Towards Data Science","postCount":749,"virtuals":{"isFollowing":false},"metadata":{"followerCount":405,"postCount":749,"coverImage":{"id":"1*oNt9G9UpVhtyFLDBwEMf8Q.png","originalWidth":2100,"originalHeight":1250,"isFeatured":true}},"type":"Tag"}],"socialRecommendsCount":0,"responsesCreatedCount":0,"links":{"entries":[{"url":"https://www.geospatial-insight.com/","alts":[],"httpStatus":200},{"url":"http://venturesone.com/venturesone-fuels-geospatial-insight/","alts":[],"httpStatus":200},{"url":"http://www.geospatial-insight.com/","alts":[],"httpStatus":200}],"version":"0.3","generatedAt":1506561626748},"isLockedPreviewOnly":false,"takeoverId":"","metaDescription":"","totalClapCount":30,"sectionCount":1,"readingList":0},"coverless":true,"slug":"hurricane-harvey-insurtech-case-study-visual-intelligence-is-transforming-claim-response-times","translationSourcePostId":"","translationSourceCreatorId":"","isApprovedTranslation":false,"inResponseToPostId":"","inResponseToRemovedAt":0,"isTitleSynthesized":true,"allowResponses":true,"importedUrl":"","importedPublishedAt":0,"visibility":0,"uniqueSlug":"hurricane-harvey-insurtech-case-study-visual-intelligence-is-transforming-claim-response-times-3275042fbd8d","previewContent":{"bodyModel":{"paragraphs":[{"name":"previewImage","type":4,"text":"","layout":10,"metadata":{"id":"1*lSrjjYyG8X2ND8hFmjBtAA.png","originalWidth":940,"originalHeight":627,"isFeatured":true}},{"name":"1f4d","type":3,"text":"Hurricane Harvey InsurTech Case Study; visual intelligence is transforming claim response times.","markups":[],"alignment":1}],"sections":[{"startIndex":0}]},"isFullContent":false},"license":0,"inResponseToMediaResourceId":"","canonicalUrl":"https://towardsdatascience.com/hurricane-harvey-insurtech-case-study-visual-intelligence-is-transforming-claim-response-times-3275042fbd8d","approvedHomeCollectionId":"7f60cf5620c9","approvedHomeCollection":{"id":"7f60cf5620c9","name":"Towards Data Science","slug":"towards-data-science","tags":["DATA SCIENCE","MACHINE LEARNING","ARTIFICIAL INTELLIGENCE","BIG DATA","ANALYTICS"],"creatorId":"895063a310f4","description":"Sharing concepts, ideas, and codes.","shortDescription":"Sharing concepts, ideas, and codes.","image":{"imageId":"1*F0LADxTtsKOgmPa-_7iUEQ.jpeg","filter":"","backgroundSize":"","originalWidth":1275,"originalHeight":1275,"strategy":"resample","height":0,"width":0},"metadata":{"followerCount":53890,"activeAt":1518560422160},"virtuals":{"permissions":{"canPublish":false,"canPublishAll":false,"canRepublish":false,"canRemove":false,"canManageAll":false,"canSubmit":false,"canEditPosts":false,"canAddWriters":false,"canViewStats":false,"canSendNewsletter":false,"canViewLockedPosts":false,"canViewCloaked":false,"canEditOwnPosts":false,"canBeAssignedAuthor":false,"canEnrollInHightower":false,"canLockPostsForMediumMembers":false},"isSubscribed":false,"isNewsletterSubscribed":false,"memberOfMembershipPlanId":"","isEnrolledInHightower":false,"isEligibleForHightower":false},"logo":{"imageId":"","filter":"","backgroundSize":"","originalWidth":0,"originalHeight":0,"strategy":"resample","height":0,"width":0},"twitterUsername":"TDataScience","facebookPageName":"towardsdatascience","publicEmail":"publication@towardsdatascience.com","collectionMastheadId":"8b6aceffde6","domain":"towardsdatascience.com","sections":[{"type":2,"collectionHeaderMetadata":{"title":"Towards Data Science","description":"Sharing concepts, ideas, and codes","backgroundImage":{},"logoImage":{},"alignment":2,"layout":5}},{"type":1,"postListMetadata":{"source":4,"layout":2,"number":1,"postIds":[],"tagSlug":"Towards Data Science"}},{"type":1,"postListMetadata":{"source":1,"layout":4,"number":6,"postIds":[],"sectionHeader":"Latest"}},{"type":1,"postListMetadata":{"source":3,"layout":4,"number":2,"postIds":["ee524ca64416","e2be7fb8d038"],"sectionHeader":"Our letters"}},{"type":3,"promoMetadata":{"sectionHeader":"","promoId":"dbabc89840b7"}},{"type":1,"postListMetadata":{"source":2,"layout":7,"number":7,"postIds":[],"sectionHeader":"Trending"}},{"type":3,"promoMetadata":{"sectionHeader":"","promoId":"69b26f0f1e35"}},{"type":1,"postListMetadata":{"source":4,"layout":4,"number":9,"postIds":[],"tagSlug":"Towards Data Science","sectionHeader":"Editors' Picks"}},{"type":3,"promoMetadata":{"sectionHeader":"","promoId":"8b04cd40f0c8"}},{"type":1,"postListMetadata":{"source":4,"layout":5,"number":3,"postIds":[],"tagSlug":"Towards Data Science","sectionHeader":"Last chance to read"}}],"tintColor":"#FF355876","lightText":true,"favicon":{"imageId":"1*F0LADxTtsKOgmPa-_7iUEQ.jpeg","filter":"","backgroundSize":"","originalWidth":1275,"originalHeight":1275,"strategy":"resample","height":0,"width":0},"colorPalette":{"defaultBackgroundSpectrum":{"colorPoints":[{"color":"#FF668AAA","point":0},{"color":"#FF61809D","point":0.1},{"color":"#FF5A7690","point":0.2},{"color":"#FF546C83","point":0.3},{"color":"#FF4D6275","point":0.4},{"color":"#FF455768","point":0.5},{"color":"#FF3D4C5A","point":0.6},{"color":"#FF34414C","point":0.7},{"color":"#FF2B353E","point":0.8},{"color":"#FF21282F","point":0.9},{"color":"#FF161B1F","point":1}],"backgroundColor":"#FFFFFFFF"},"tintBackgroundSpectrum":{"colorPoints":[{"color":"#FF355876","point":0},{"color":"#FF4D6C88","point":0.1},{"color":"#FF637F99","point":0.2},{"color":"#FF7791A8","point":0.3},{"color":"#FF8CA2B7","point":0.4},{"color":"#FF9FB3C6","point":0.5},{"color":"#FFB2C3D4","point":0.6},{"color":"#FFC5D2E1","point":0.7},{"color":"#FFD7E2EE","point":0.8},{"color":"#FFE9F1FA","point":0.9},{"color":"#FFFBFFFF","point":1}],"backgroundColor":"#FF355876"},"highlightSpectrum":{"colorPoints":[{"color":"#FFEDF4FC","point":0},{"color":"#FFE9F2FD","point":0.1},{"color":"#FFE6F1FD","point":0.2},{"color":"#FFE2EFFD","point":0.3},{"color":"#FFDFEEFD","point":0.4},{"color":"#FFDBECFE","point":0.5},{"color":"#FFD7EBFE","point":0.6},{"color":"#FFD4E9FE","point":0.7},{"color":"#FFD0E7FF","point":0.8},{"color":"#FFCCE6FF","point":0.9},{"color":"#FFC8E4FF","point":1}],"backgroundColor":"#FFFFFFFF"}},"navItems":[{"type":4,"title":"Data Science","url":"https://towardsdatascience.com/data-science/home","topicId":"cf416843aadc","source":"topicId"},{"type":4,"title":"Machine Learning","url":"https://towardsdatascience.com/machine-learning/home","topicId":"a5c9b2f1cb6b","source":"topicId"},{"type":4,"title":"Programming","url":"https://towardsdatascience.com/programming/home","topicId":"41533a1dc73c","source":"topicId"},{"type":4,"title":"Visualization","url":"https://towardsdatascience.com/data-visualization/home","topicId":"825e6cb8b9ce","source":"topicId"},{"type":4,"title":"Letters","url":"https://towardsdatascience.com/newsletters/home","topicId":"83f438f06a8c","source":"topicId"},{"type":4,"title":"Contribute","url":"https://towardsdatascience.com/contribute/home","topicId":"6ae0c8697d8c","source":"topicId"},{"type":3,"title":"Become a Patreon","url":"https://www.patreon.com/towardsdatascience/"}],"colorBehavior":2,"instantArticlesState":0,"acceleratedMobilePagesState":0,"googleAnalyticsId":"UA-19707169-24","ampLogo":{"imageId":"","filter":"","backgroundSize":"","originalWidth":0,"originalHeight":0,"strategy":"resample","height":0,"width":0},"header":{"title":"Towards Data Science","description":"Sharing concepts, ideas, and codes","backgroundImage":{},"logoImage":{},"alignment":2,"layout":5},"paidForDomainAt":1509037374118,"type":"Collection"},"newsletterId":"","webCanonicalUrl":"https://towardsdatascience.com/hurricane-harvey-insurtech-case-study-visual-intelligence-is-transforming-claim-response-times-3275042fbd8d","mediumUrl":"https://towardsdatascience.com/hurricane-harvey-insurtech-case-study-visual-intelligence-is-transforming-claim-response-times-3275042fbd8d","migrationId":"","notifyFollowers":true,"notifyTwitter":false,"isSponsored":false,"isRequestToPubDisabled":false,"notifyFacebook":false,"responseHiddenOnParentPostAt":0,"isSeries":false,"isSubscriptionLocked":false,"seriesLastAppendedAt":0,"audioVersionDurationSec":0,"sequenceId":"","isNsfw":false,"isEligibleForRevenue":false,"isBlockedFromHightower":false,"deletedAt":0,"lockedPostSource":0,"hightowerMinimumGuaranteeStartsAt":0,"hightowerMinimumGuaranteeEndsAt":0,"featureLockRequestAcceptedAt":0,"featureLockRequestMinimumGuaranteeAmount":0,"isElevate":false,"type":"Post"},"mentionedUsers":[],"collaborators":[],"membershipPlans":[],"collectionUserRelations":[],"mode":null,"references":{"User":{"44ee44e12515":{"userId":"44ee44e12515","name":"Rafael Aldon","username":"raldon","createdAt":1491556308897,"lastPostCreatedAt":1505710391517,"imageId":"1*xyfTiylyHHiLyxJTJQy8AQ.png","backgroundImageId":"","bio":"Early-Stage Venture Capital in Asia | Tech Investor | Startup Advisor | FinTech & Blockchain Enthusiast | Formula 1 Nut","twitterScreenName":"","socialStats":{"userId":"44ee44e12515","usersFollowedCount":34,"usersFollowedByCount":11,"type":"SocialStats"},"social":{"userId":"lo_Pde0GEfT2sEl","targetUserId":"44ee44e12515","type":"Social"},"facebookAccountId":"","allowNotes":1,"isNsfw":false,"type":"User"}},"Collection":{"7f60cf5620c9":{"id":"7f60cf5620c9","name":"Towards Data Science","slug":"towards-data-science","tags":["DATA SCIENCE","MACHINE LEARNING","ARTIFICIAL INTELLIGENCE","BIG DATA","ANALYTICS"],"creatorId":"895063a310f4","description":"Sharing concepts, ideas, and codes.","shortDescription":"Sharing concepts, ideas, and codes.","image":{"imageId":"1*F0LADxTtsKOgmPa-_7iUEQ.jpeg","filter":"","backgroundSize":"","originalWidth":1275,"originalHeight":1275,"strategy":"resample","height":0,"width":0},"metadata":{"followerCount":53890,"activeAt":1518560422160},"virtuals":{"permissions":{"canPublish":false,"canPublishAll":false,"canRepublish":false,"canRemove":false,"canManageAll":false,"canSubmit":false,"canEditPosts":false,"canAddWriters":false,"canViewStats":false,"canSendNewsletter":false,"canViewLockedPosts":false,"canViewCloaked":false,"canEditOwnPosts":false,"canBeAssignedAuthor":false,"canEnrollInHightower":false,"canLockPostsForMediumMembers":false},"isSubscribed":false,"isNewsletterSubscribed":false,"memberOfMembershipPlanId":"","isEnrolledInHightower":false,"isEligibleForHightower":false},"logo":{"imageId":"","filter":"","backgroundSize":"","originalWidth":0,"originalHeight":0,"strategy":"resample","height":0,"width":0},"twitterUsername":"TDataScience","facebookPageName":"towardsdatascience","publicEmail":"publication@towardsdatascience.com","collectionMastheadId":"8b6aceffde6","domain":"towardsdatascience.com","sections":[{"type":2,"collectionHeaderMetadata":{"title":"Towards Data Science","description":"Sharing concepts, ideas, and codes","backgroundImage":{},"logoImage":{},"alignment":2,"layout":5}},{"type":1,"postListMetadata":{"source":4,"layout":2,"number":1,"postIds":[],"tagSlug":"Towards Data Science"}},{"type":1,"postListMetadata":{"source":1,"layout":4,"number":6,"postIds":[],"sectionHeader":"Latest"}},{"type":1,"postListMetadata":{"source":3,"layout":4,"number":2,"postIds":["ee524ca64416","e2be7fb8d038"],"sectionHeader":"Our letters"}},{"type":3,"promoMetadata":{"sectionHeader":"","promoId":"dbabc89840b7"}},{"type":1,"postListMetadata":{"source":2,"layout":7,"number":7,"postIds":[],"sectionHeader":"Trending"}},{"type":3,"promoMetadata":{"sectionHeader":"","promoId":"69b26f0f1e35"}},{"type":1,"postListMetadata":{"source":4,"layout":4,"number":9,"postIds":[],"tagSlug":"Towards Data Science","sectionHeader":"Editors' Picks"}},{"type":3,"promoMetadata":{"sectionHeader":"","promoId":"8b04cd40f0c8"}},{"type":1,"postListMetadata":{"source":4,"layout":5,"number":3,"postIds":[],"tagSlug":"Towards Data Science","sectionHeader":"Last chance to read"}}],"tintColor":"#FF355876","lightText":true,"favicon":{"imageId":"1*F0LADxTtsKOgmPa-_7iUEQ.jpeg","filter":"","backgroundSize":"","originalWidth":1275,"originalHeight":1275,"strategy":"resample","height":0,"width":0},"colorPalette":{"defaultBackgroundSpectrum":{"colorPoints":[{"color":"#FF668AAA","point":0},{"color":"#FF61809D","point":0.1},{"color":"#FF5A7690","point":0.2},{"color":"#FF546C83","point":0.3},{"color":"#FF4D6275","point":0.4},{"color":"#FF455768","point":0.5},{"color":"#FF3D4C5A","point":0.6},{"color":"#FF34414C","point":0.7},{"color":"#FF2B353E","point":0.8},{"color":"#FF21282F","point":0.9},{"color":"#FF161B1F","point":1}],"backgroundColor":"#FFFFFFFF"},"tintBackgroundSpectrum":{"colorPoints":[{"color":"#FF355876","point":0},{"color":"#FF4D6C88","point":0.1},{"color":"#FF637F99","point":0.2},{"color":"#FF7791A8","point":0.3},{"color":"#FF8CA2B7","point":0.4},{"color":"#FF9FB3C6","point":0.5},{"color":"#FFB2C3D4","point":0.6},{"color":"#FFC5D2E1","point":0.7},{"color":"#FFD7E2EE","point":0.8},{"color":"#FFE9F1FA","point":0.9},{"color":"#FFFBFFFF","point":1}],"backgroundColor":"#FF355876"},"highlightSpectrum":{"colorPoints":[{"color":"#FFEDF4FC","point":0},{"color":"#FFE9F2FD","point":0.1},{"color":"#FFE6F1FD","point":0.2},{"color":"#FFE2EFFD","point":0.3},{"color":"#FFDFEEFD","point":0.4},{"color":"#FFDBECFE","point":0.5},{"color":"#FFD7EBFE","point":0.6},{"color":"#FFD4E9FE","point":0.7},{"color":"#FFD0E7FF","point":0.8},{"color":"#FFCCE6FF","point":0.9},{"color":"#FFC8E4FF","point":1}],"backgroundColor":"#FFFFFFFF"}},"navItems":[{"type":4,"title":"Data Science","url":"https://towardsdatascience.com/data-science/home","topicId":"cf416843aadc","source":"topicId"},{"type":4,"title":"Machine Learning","url":"https://towardsdatascience.com/machine-learning/home","topicId":"a5c9b2f1cb6b","source":"topicId"},{"type":4,"title":"Programming","url":"https://towardsdatascience.com/programming/home","topicId":"41533a1dc73c","source":"topicId"},{"type":4,"title":"Visualization","url":"https://towardsdatascience.com/data-visualization/home","topicId":"825e6cb8b9ce","source":"topicId"},{"type":4,"title":"Letters","url":"https://towardsdatascience.com/newsletters/home","topicId":"83f438f06a8c","source":"topicId"},{"type":4,"title":"Contribute","url":"https://towardsdatascience.com/contribute/home","topicId":"6ae0c8697d8c","source":"topicId"},{"type":3,"title":"Become a Patreon","url":"https://www.patreon.com/towardsdatascience/"}],"colorBehavior":2,"instantArticlesState":0,"acceleratedMobilePagesState":0,"googleAnalyticsId":"UA-19707169-24","ampLogo":{"imageId":"","filter":"","backgroundSize":"","originalWidth":0,"originalHeight":0,"strategy":"resample","height":0,"width":0},"header":{"title":"Towards Data Science","description":"Sharing concepts, ideas, and codes","backgroundImage":{},"logoImage":{},"alignment":2,"layout":5},"paidForDomainAt":1509037374118,"type":"Collection"}},"Social":{"44ee44e12515":{"userId":"lo_Pde0GEfT2sEl","targetUserId":"44ee44e12515","type":"Social"}},"SocialStats":{"44ee44e12515":{"userId":"44ee44e12515","usersFollowedCount":34,"usersFollowedByCount":11,"type":"SocialStats"}}}})
// ]]></script></body></html>