{"id":1847,"date":"2015-10-31T12:53:18","date_gmt":"2015-10-31T16:53:18","guid":{"rendered":"https:\/\/digital.hbs.edu\/platform-digit\/submission\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\/"},"modified":"2015-10-31T12:55:05","modified_gmt":"2015-10-31T16:55:05","slug":"the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations","status":"publish","type":"hck-submission","link":"https:\/\/d3.harvard.edu\/platform-digit\/submission\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\/","title":{"rendered":"The Netflix Prize: Crowdsourcing to Improve DVD Recommendations"},"content":{"rendered":"<p>In 2006, Neflix launched the Netflix Prize, &#8220;a machine learning and data mining competition for movie rating prediction.&#8221; Netflix hoped the $1 million prize would encourage a range of algorithmic solutions to improve the company&#8217;s existing recommendation program, <em>Cinematch<\/em>,\u00a0by 10%.\u00a0<em>Cinematch\u00a0<\/em>used &#8220;straightforward statistical linear models with a lot of data conditioning,&#8221; and served two major purposes: as a competitive differentiator by recommending unfamiliar movies to customers, and more importantly, enabled Netflix to reduce demand for blockbuster new releases and improve assets turns of all DVDs in inventory.<\/p>\n<p><strong>Project Scope:\u00a0<\/strong>Netflix defined the project scope as a 10% reduction of the &#8220;root mean squared error&#8221; (RMSE) from\u00a0<em>Cinematch&#8217;s<\/em> existing 0.9525, and set a series of <a href=\"http:\/\/www.netflixprize.com\/faq#prize\" target=\"_blank\">guidelines<\/a> for competition participants. Netflix provided\u00a0\u00a0a dataset containing 100 million anonymous movie ratings for participants to test their algorithms.<\/p>\n<p><b>2007 Progress Prize:\u00a0<\/b>In 2007, the BellKor\u00a0Team, comprised of three employees from the Statistics Research group in AT&amp;T labs, achieved an 8.43% improvement over\u00a0<em>Cinematch<\/em>, and were awarded the first of two $50,000 Progress Prizes. The team spent nearly 2,000 developing a final\u00a0<a href=\"http:\/\/www.netflixprize.com\/assets\/ProgressPrize2007_KorBell.pdf\" target=\"_blank\">solution<\/a>\u00a0that contained 107 algorithms and achieved a RMSE of 0.8712. Netflix engineers investigated the source code (a requirement for the prize), and identified the two best performing algorithms (of the 107): Matrix Foundation (also known as Singular Value Decomposition (SVD)) and Restricted Boltzmann Machines (RBM). &#8220;A linear blend&#8221; of the two algorithms were ultimately put to use in Netflix&#8217;s recommendation system, but the company\u00a0set a goal of 1% improvement over BellKor&#8217;s solution to receive the 2008 Progress Prize.<\/p>\n<p><a href=\"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/netflix_winners_2_star-medi.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"size-medium wp-image-1832 aligncenter\" src=\"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/netflix_winners_2_star-medi-263x300.jpg\" alt=\"netflix_winners_2_star-medi\" width=\"263\" height=\"300\" srcset=\"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/netflix_winners_2_star-medi-263x300.jpg 263w, https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/netflix_winners_2_star-medi.jpg 378w\" sizes=\"auto, (max-width: 263px) 100vw, 263px\" \/><\/a><\/p>\n<div><strong>2008 Progress Prize:\u00a0<\/strong>The BellKor in BigChaos (the original BellKor team combined forces with colleagues from\u00a0colleagues from Commendo Research) team won the second Progress Prize with an RMSE of 0.8627 and a 9.44% improvement over\u00a0<em>Cinematch.<\/em><\/div>\n<div><\/div>\n<div><strong>2009 Grand Prize:<\/strong> With 24 minutes remaining before the close of the 3-year contest, Bellkor&#8217;s Pragmatic Chaos, a further expansion of the original BellKor team, submitted the ultimate $1 million grand prize solution. The final set of algorithms achieved an RMSE of 0.8567 and a 10.06% improvement over\u00a0<em>Cinematch<\/em>.<\/div>\n<div><a href=\"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/bigcheck.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"size-medium wp-image-1835 aligncenter\" src=\"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/bigcheck-300x197.jpg\" alt=\"bigcheck\" width=\"300\" height=\"197\" srcset=\"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/bigcheck-300x197.jpg 300w, https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/bigcheck.jpg 594w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a><\/div>\n<div><\/div>\n<div>The entire three year contest included 51,051 contestants and 41,305 teams (representing 186 countries). Netflix ultimately received 44,014 valid submission from 5,169 teams.<\/div>\n<div><a href=\"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/leaderboard.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"size-medium wp-image-1836 alignleft\" src=\"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/leaderboard-300x236.jpg\" alt=\"leaderboard\" width=\"300\" height=\"236\" srcset=\"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/leaderboard-300x236.jpg 300w, https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/leaderboard-1024x804.jpg 1024w, https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/leaderboard-600x471.jpg 600w, https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/leaderboard.jpg 1025w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a><\/div>\n<div><\/div>\n<div><a href=\"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/Capture1.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\" wp-image-1837 alignleft\" src=\"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/Capture1-300x142.jpg\" alt=\"Capture\" width=\"357\" height=\"169\" srcset=\"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/Capture1-300x142.jpg 300w, https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/Capture1-600x285.jpg 600w, https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/Capture1.jpg 803w\" sizes=\"auto, (max-width: 357px) 100vw, 357px\" \/><\/a><\/div>\n<div><\/div>\n<div><\/div>\n<div><a href=\"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/bellmath.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-1838\" src=\"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/bellmath-300x130.jpg\" alt=\"bellmath\" width=\"300\" height=\"130\" srcset=\"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/bellmath-300x130.jpg 300w, https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/bellmath.jpg 497w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/a><\/div>\n<div><\/div>\n<div><\/div>\n<div><\/div>\n<div><strong>Crowdsourcing:<\/strong>\u00a0At each stage of the contest the original BellKor team expanded by adding new members, or in the case of the final submission, an entire competing team, to further refine their algorithms and drive for a &gt;10% improvement. Second place finisher &#8220;The Ensemble&#8221; also formed as a collection of teams that had submitted individual solutions earlier in the contest. <a href=\"http:\/\/www.wired.com\/2009\/09\/how-the-netflix-prize-was-won\/\" target=\"_blank\">Wired <\/a>magazine summarized this crowdsourcing within a crowdsourcing competition: &#8220;The secret sauce for both BellKor\u2019s Pragmatic Chaos and The Ensemble was collaboration between diverse ideas, and not in some touchy-feely, unquantifiable, &#8216;when people work together things are better&#8217; sort of way. The top two teams beat the challenge by combining teams and their algorithms into more complex algorithms incorporating everybody\u2019s work. The more people joined, the more the resulting team\u2019s score would increase.&#8221;<\/div>\n<div><\/div>\n<div>\u201cAt first, a whole lot of teams got in \u2014 and they got 6-percent improvement, 7-percent improvement, 8-percent improvement, and then it started slowing down, and we got into year two. There was this long period where they were barely making progress, and we were thinking, \u2018maybe this will never be won&#8230;\u2019\u00a0Then there was a great insight among some of the teams \u2014 that if they combined their approaches, they actually got better. It was fairly unintuitive to many people [because you generally take the smartest two people and say \u2018come up with a solution\u2019]\u2026 when you get this combining of these algorithms in certain ways, it started out this \u2018second frenzy.\u2019 In combination, the teams could get better and better and better,\u201d\u00a0\u00a0explained\u00a0 Netflix chief product officer Neil Hunt.<\/div>\n<div><\/div>\n<div>\n<p>When it was an independent team, Pragmatic Theory, discovered that the number of movies rated by an individual on an given day could be used as an indicator of how much time had passed since the viewer watched the movie. They also tracked &#8220;how memory affected particular movie ratings.&#8221;\u00a0(ed. note: unclear how this was done). Although this discovery was not particular successful on its own at achieving the &gt;10% improvement, when combined with BellKor&#8217;s algorithms, it gave the new team a slight edge over the competition.<\/p>\n<\/div>\n<div>The Netflix Prize demonstrates the power of crowdsourcing in developing innovative solutions for complex problems. Further, it&#8217;s an interesting example of how setting various stages in the competition can help further push teams to achieve new success by combining their solutions with other contestants.<\/div>\n<div><\/div>\n<div><\/div>\n<div><\/div>\n","protected":false},"excerpt":{"rendered":"<p>Netflix utilized crowdsourcing to develop innovative solution to improve its recommendation engine by 10%. The 3-year Netflix Prize attracted 44,014 submissions, and was ultimately won by a team that had combined algorithms after the second year of the contest, proving that you can crowdsource a crowdsource.  <\/p>\n","protected":false},"author":32,"featured_media":1848,"comment_status":"open","ping_status":"closed","template":"","categories":[773,673,772,90],"class_list":["post-1847","hck-submission","type-hck-submission","status-publish","has-post-thumbnail","hentry","category-algo","category-crowdsourcing","category-crowdsourcing-x2","category-netflix"],"connected_submission_link":"https:\/\/d3.harvard.edu\/platform-digit\/assignment\/leveraging-the-collective-intelligence-and-effort-of-digital-crowds\/","yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.3 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>The Netflix Prize: Crowdsourcing to Improve DVD Recommendations - Digital Innovation and Transformation<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/d3.harvard.edu\/platform-digit\/submission\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"The Netflix Prize: Crowdsourcing to Improve DVD Recommendations - Digital Innovation and Transformation\" \/>\n<meta property=\"og:description\" content=\"Netflix utilized crowdsourcing to develop innovative solution to improve its recommendation engine by 10%. The 3-year Netflix Prize attracted 44,014 submissions, and was ultimately won by a team that had combined algorithms after the second year of the contest, proving that you can crowdsource a crowdsource.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/d3.harvard.edu\/platform-digit\/submission\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\/\" \/>\n<meta property=\"og:site_name\" content=\"Digital Innovation and Transformation\" \/>\n<meta property=\"article:modified_time\" content=\"2015-10-31T16:55:05+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/netflix.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"675\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-digit\\\/submission\\\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\\\/\",\"url\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-digit\\\/submission\\\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\\\/\",\"name\":\"The Netflix Prize: Crowdsourcing to Improve DVD Recommendations - Digital Innovation and Transformation\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-digit\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-digit\\\/submission\\\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-digit\\\/submission\\\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-digit\\\/wp-content\\\/uploads\\\/sites\\\/2\\\/2015\\\/10\\\/netflix.png\",\"datePublished\":\"2015-10-31T16:53:18+00:00\",\"dateModified\":\"2015-10-31T16:55:05+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-digit\\\/submission\\\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/d3.harvard.edu\\\/platform-digit\\\/submission\\\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-digit\\\/submission\\\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\\\/#primaryimage\",\"url\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-digit\\\/wp-content\\\/uploads\\\/sites\\\/2\\\/2015\\\/10\\\/netflix.png\",\"contentUrl\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-digit\\\/wp-content\\\/uploads\\\/sites\\\/2\\\/2015\\\/10\\\/netflix.png\",\"width\":1200,\"height\":675},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-digit\\\/submission\\\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-digit\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Submissions\",\"item\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-digit\\\/submission\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"The Netflix Prize: Crowdsourcing to Improve DVD Recommendations\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-digit\\\/#website\",\"url\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-digit\\\/\",\"name\":\"Digital Innovation and Transformation\",\"description\":\"MBA Student Perspectives\",\"potentialAction\":[{\"@type\":\"性视界Action\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-digit\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"The Netflix Prize: Crowdsourcing to Improve DVD Recommendations - Digital Innovation and Transformation","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/d3.harvard.edu\/platform-digit\/submission\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\/","og_locale":"en_US","og_type":"article","og_title":"The Netflix Prize: Crowdsourcing to Improve DVD Recommendations - Digital Innovation and Transformation","og_description":"Netflix utilized crowdsourcing to develop innovative solution to improve its recommendation engine by 10%. The 3-year Netflix Prize attracted 44,014 submissions, and was ultimately won by a team that had combined algorithms after the second year of the contest, proving that you can crowdsource a crowdsource.","og_url":"https:\/\/d3.harvard.edu\/platform-digit\/submission\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\/","og_site_name":"Digital Innovation and Transformation","article_modified_time":"2015-10-31T16:55:05+00:00","og_image":[{"width":1200,"height":675,"url":"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/netflix.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/d3.harvard.edu\/platform-digit\/submission\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\/","url":"https:\/\/d3.harvard.edu\/platform-digit\/submission\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\/","name":"The Netflix Prize: Crowdsourcing to Improve DVD Recommendations - Digital Innovation and Transformation","isPartOf":{"@id":"https:\/\/d3.harvard.edu\/platform-digit\/#website"},"primaryImageOfPage":{"@id":"https:\/\/d3.harvard.edu\/platform-digit\/submission\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\/#primaryimage"},"image":{"@id":"https:\/\/d3.harvard.edu\/platform-digit\/submission\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\/#primaryimage"},"thumbnailUrl":"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/netflix.png","datePublished":"2015-10-31T16:53:18+00:00","dateModified":"2015-10-31T16:55:05+00:00","breadcrumb":{"@id":"https:\/\/d3.harvard.edu\/platform-digit\/submission\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/d3.harvard.edu\/platform-digit\/submission\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/d3.harvard.edu\/platform-digit\/submission\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\/#primaryimage","url":"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/netflix.png","contentUrl":"https:\/\/d3.harvard.edu\/platform-digit\/wp-content\/uploads\/sites\/2\/2015\/10\/netflix.png","width":1200,"height":675},{"@type":"BreadcrumbList","@id":"https:\/\/d3.harvard.edu\/platform-digit\/submission\/the-netflix-prize-crowdsourcing-to-improve-dvd-recommendations\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/d3.harvard.edu\/platform-digit\/"},{"@type":"ListItem","position":2,"name":"Submissions","item":"https:\/\/d3.harvard.edu\/platform-digit\/submission\/"},{"@type":"ListItem","position":3,"name":"The Netflix Prize: Crowdsourcing to Improve DVD Recommendations"}]},{"@type":"WebSite","@id":"https:\/\/d3.harvard.edu\/platform-digit\/#website","url":"https:\/\/d3.harvard.edu\/platform-digit\/","name":"Digital Innovation and Transformation","description":"MBA Student Perspectives","potentialAction":[{"@type":"性视界Action","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/d3.harvard.edu\/platform-digit\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/d3.harvard.edu\/platform-digit\/wp-json\/wp\/v2\/hck-submission\/1847","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/d3.harvard.edu\/platform-digit\/wp-json\/wp\/v2\/hck-submission"}],"about":[{"href":"https:\/\/d3.harvard.edu\/platform-digit\/wp-json\/wp\/v2\/types\/hck-submission"}],"author":[{"embeddable":true,"href":"https:\/\/d3.harvard.edu\/platform-digit\/wp-json\/wp\/v2\/users\/32"}],"replies":[{"embeddable":true,"href":"https:\/\/d3.harvard.edu\/platform-digit\/wp-json\/wp\/v2\/comments?post=1847"}],"version-history":[{"count":0,"href":"https:\/\/d3.harvard.edu\/platform-digit\/wp-json\/wp\/v2\/hck-submission\/1847\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/d3.harvard.edu\/platform-digit\/wp-json\/wp\/v2\/media\/1848"}],"wp:attachment":[{"href":"https:\/\/d3.harvard.edu\/platform-digit\/wp-json\/wp\/v2\/media?parent=1847"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/d3.harvard.edu\/platform-digit\/wp-json\/wp\/v2\/categories?post=1847"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}