{"id":34254,"date":"2018-11-13T17:59:40","date_gmt":"2018-11-13T22:59:40","guid":{"rendered":"https:\/\/digital.hbs.edu\/platform-rctom\/submission\/ml-and-chill-machine-learning-at-netflix\/"},"modified":"2018-11-13T17:59:40","modified_gmt":"2018-11-13T22:59:40","slug":"ml-and-chill-machine-learning-at-netflix","status":"publish","type":"hck-submission","link":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/ml-and-chill-machine-learning-at-netflix\/","title":{"rendered":"ML and Chill: Machine learning at Netflix"},"content":{"rendered":"

Hollywood studios have struggled with a core problem for over a century: How can an organization scale a creative endeavor? Movies and television shows require fresh ideas to be successful, yet studios must have processes in place to produce multiple hits. Further complicating this challenge, consumer preferences have shifted from movie theaters to streaming services, so studios must present their content on a user interface that retains monthly subscribers. As Wall Street Journal columnist Elizabeth Winkler writes, \u201cThe definition of success has shifted from how many eyeballs a channel can grab on a given night to how effectively a piece of content helps retain subscribers month after month.\u201d[1]<\/a> Los Gatos-based Netflix, Inc. has taken a unique approach by solving these problems with machine learning.<\/p>\n

In the short term, Netflix uses machine learning to optimize both its frontend interface and its backend operations, creating a better experience for its users. Netflix\u2019s user interface is essential for capturing a viewer\u2019s attention; internally, teams at Netflix refer to the first ten seconds a user spends on the homepage as the \u201cmoment of truth,\u201d as the user will quickly decide whether Netflix has any shows they want to watch.[2]<\/a> In order to increase the likelihood a user will watch a show, Netflix has several different previews for each title, and it uses machine learning to match a preview to a user\u2019s demonstrated preferences. For example, the preview for Good Will Hunting may change depending whether a user prefers romance, in which case it will feature a photo of costars Matt Damon and Minnie Driver, or comedy, in which case it will feature comedian Robin Williams.[3]<\/a><\/p>\n

\"\"<\/a>
Optimized previews for Good Will Hunting (The Netflix Tech Blog)<\/figcaption><\/figure>\n

Machine learning can also improve a company\u2019s backend operations, and Netflix has applied the technology to improve its streaming quality. With over 100 million users across the globe and over 1000 different devices streaming its content, Netflix needs to provide an array of streaming solutions if it wants to retain its customers.[4]<\/a> For example, the network bandwidth available for a mobile user in India will be significantly different than a SmartTV user in the United States. The engineering team at Netflix employs machine learning to predict the network needs of a device, which allows the company to optimize its server load while avoiding video delays.[5]<\/a> It should be noted that both of these applications of machine learning \u2014 frontend customization and backend optimization \u2014 directly impact the user experience, which in turn reduces customer churn.<\/p>\n

In the long term, Netflix uses machine learning to determine which content to produce. The company will be releasing over 700 original shows and movies this year, and many of the greenlight decisions are influenced by the company\u2019s machine learning algorithm.[6]<\/a> Netflix\u2019s data about its content comes from two key sources; the first is a group of \u201ctaggers\u201d who categorize content with attributes like \u201cgritty drama.\u201d[7]<\/a> The second source is Netflix\u2019s userbase; the company relies on groups of implicit and explicit data. Explicit data come from stated user preferences and include thumbs up\/down ratings; implicit data come from user actions and include the clickthrough and completion rates for each piece of content.[8]<\/a> By harnessing this powerful set of data, Netflix has created an unmatched recommendation engine. Over 80 percent of viewership on the platform comes from algorithm suggestions, and Netflix then harnesses this data to make forward-looking decisions about which content to produce next.\u00a0[9]<\/a><\/p>\n

While Netflix has been very successful with its application of machine learning, there are still some potential pitfalls as an over-reliance on implicit data could lead to negative outcomes. An example of such an outcome can be seen at YouTube, where optimization for implicit user engagement led its algorithm to consistently steer users towards \u201cdivisive, misleading or false content.\u201d\u00a0[10]<\/a> While users were more likely to watch YouTube\u2019s extremist content for longer, this short-term optimization risked generating long-term user mistrust and government regulation. Netflix has taken steps to decrease its use of explicit data by removing all user reviews,[11]<\/a> and I believe this choice creates risks similar to those YouTube faced. If Netflix wants to avoid YouTube’s over-optimization mistake, it will need to keep using explicit data.<\/p>\n

So far the Netflix algorithm has successfully avoided these local optimums by avoiding overreliance on any type of content, and it continues to pick new shows and movies successfully. Yet as the studio grows, it will sign bigger and bigger stars, and it may need to consider the human impact of its reliance on machine learning. When a long-term business deal collides with a machine learning algorithm, how can Netflix know when to trust its algorithm instead of its business development team? The company is grappling with this question today,[12]<\/a> and if recent events are any guide, Netflix\u2019s decision will influence the entire entertainment industry.<\/p>\n

(794 words)<\/p>\n

[1]<\/a> Winkler, Elizabeth. 2018. \u201cWhy No One Can Catch Netflix.\u201d The Wall Street Journal<\/i>. Dow Jones & Company. August 26. https:\/\/www.wsj.com\/articles\/why-no-one-can-catch-netflix-1535205600.<\/p>\n

[2]<\/a> Ramachandran, Shalini, and Joe Flint. 2018. \u201cAt Netflix, Who Wins When It’s Hollywood vs. the Algorithm?\u201d The Wall Street Journal<\/i>. Dow Jones & Company. November 10. https:\/\/www.wsj.com\/articles\/at-netflix-who-wins-when-its-hollywood-vs-the-algorithm-1541826015.<\/p>\n

[3]<\/a> Chandrashekar, Ashok, Fernando Amat, Justin Basilico, and Tony Jebara. “Artwork Personalization at Netflix \u2013 Netflix TechBlog \u2013 Medium.” The Netflix Tech Blog. December 07, 2017. Accessed November 13, 2018. https:\/\/medium.com\/netflix-techblog\/artwork-personalization-c589f074ad76.<\/p>\n

[4]<\/a>\u00a0Ekanadham, Chaitanya. 2018. \u201cUsing Machine Learning to Improve Streaming Quality at Netflix.\u201d The Netflix Technology Blog<\/i>. Netflix. March 22. https:\/\/medium.com\/netflix-techblog\/using-machine-learning-to-improve-streaming-quality-at-netflix-9651263ef09f.<\/p>\n

[5]<\/a>\u00a0Ibid.<\/p>\n

[6]<\/a>\u00a0Ramachandran and Flint.<\/p>\n

[7]<\/a>\u00a0Plummer, Libby. 2017. \u201cThis Is How Netflix’s Top-Secret Recommendation System Works.\u201d WIRED<\/i>. WIRED UK. August 21. https:\/\/www.wired.co.uk\/article\/how-do-netflixs-algorithms-work-machine-learning-helps-to-predict-what-viewers-will-like.<\/p>\n

[8]<\/a>\u00a0Ibid.<\/p>\n

[9]<\/a>\u00a0Ibid.<\/p>\n

[10]<\/a>\u00a0Nicas, Jack. 2018. \u201cHow YouTube Drives People to the Internet’s Darkest Corners.\u201d The Wall Street Journal<\/i>. Dow Jones & Company. February 7. https:\/\/www.wsj.com\/articles\/how-youtube-drives-viewers-to-the-internets-darkest-corners-1518020478.<\/p>\n

[11]<\/a>\u00a0Spangler, Todd. 2018. \u201cNetflix Has Deleted All User Reviews From Its Website.\u201d Variety<\/i>. Variety. August 19. https:\/\/variety.com\/2018\/digital\/news\/netflix-deletes-all-user-reviews-1202908904\/.<\/p>\n

[12]<\/a>\u00a0Ramachandran and Flint.<\/p>\n","protected":false},"excerpt":{"rendered":"

Netflix uses machine learning based on implicit data in nearly every part of the user experience \u2014 but what risks does this approach create?<\/p>\n","protected":false},"author":11096,"featured_media":34416,"comment_status":"open","ping_status":"closed","template":"","categories":[346],"class_list":["post-34254","hck-submission","type-hck-submission","status-publish","has-post-thumbnail","hentry","category-machine-learning","hck-taxonomy-organization-netflix","hck-taxonomy-industry-technology","hck-taxonomy-country-united-states"],"connected_submission_link":"https:\/\/d3.harvard.edu\/platform-rctom\/assignment\/rc-tom-challenge-2018\/","yoast_head":"\nML and Chill: Machine learning at Netflix - Technology and Operations Management<\/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-rctom\/submission\/ml-and-chill-machine-learning-at-netflix\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"ML and Chill: Machine learning at Netflix - Technology and Operations Management\" \/>\n<meta property=\"og:description\" content=\"Netflix uses machine learning based on implicit data in nearly every part of the user experience \u2014 but what risks does this approach create?\" \/>\n<meta property=\"og:url\" content=\"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/ml-and-chill-machine-learning-at-netflix\/\" \/>\n<meta property=\"og:site_name\" content=\"Technology and Operations Management\" \/>\n<meta property=\"og:image\" content=\"https:\/\/d3.harvard.edu\/platform-rctom\/wp-content\/uploads\/sites\/4\/2018\/11\/edc0298a-b9a0-11e7-9274-06c476b5c346_aim_1024w-1.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1024\" \/>\n\t<meta property=\"og:image:height\" content=\"576\" \/>\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=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/ml-and-chill-machine-learning-at-netflix\\\/\",\"url\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/ml-and-chill-machine-learning-at-netflix\\\/\",\"name\":\"ML and Chill: Machine learning at Netflix - Technology and Operations Management\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/ml-and-chill-machine-learning-at-netflix\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/ml-and-chill-machine-learning-at-netflix\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2018\\\/11\\\/edc0298a-b9a0-11e7-9274-06c476b5c346_aim_1024w-1.png\",\"datePublished\":\"2018-11-13T22:59:40+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/ml-and-chill-machine-learning-at-netflix\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/ml-and-chill-machine-learning-at-netflix\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/ml-and-chill-machine-learning-at-netflix\\\/#primaryimage\",\"url\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2018\\\/11\\\/edc0298a-b9a0-11e7-9274-06c476b5c346_aim_1024w-1.png\",\"contentUrl\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/wp-content\\\/uploads\\\/sites\\\/4\\\/2018\\\/11\\\/edc0298a-b9a0-11e7-9274-06c476b5c346_aim_1024w-1.png\",\"width\":1024,\"height\":576},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/ml-and-chill-machine-learning-at-netflix\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Submissions\",\"item\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/submission\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"ML and Chill: Machine learning at Netflix\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/#website\",\"url\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/\",\"name\":\"Technology and Operations Management\",\"description\":\"MBA Student Perspectives\",\"potentialAction\":[{\"@type\":\"性视界Action\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/d3.harvard.edu\\\/platform-rctom\\\/?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":"ML and Chill: Machine learning at Netflix - Technology and Operations Management","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-rctom\/submission\/ml-and-chill-machine-learning-at-netflix\/","og_locale":"en_US","og_type":"article","og_title":"ML and Chill: Machine learning at Netflix - Technology and Operations Management","og_description":"Netflix uses machine learning based on implicit data in nearly every part of the user experience \u2014 but what risks does this approach create?","og_url":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/ml-and-chill-machine-learning-at-netflix\/","og_site_name":"Technology and Operations Management","og_image":[{"width":1024,"height":576,"url":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-content\/uploads\/sites\/4\/2018\/11\/edc0298a-b9a0-11e7-9274-06c476b5c346_aim_1024w-1.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/ml-and-chill-machine-learning-at-netflix\/","url":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/ml-and-chill-machine-learning-at-netflix\/","name":"ML and Chill: Machine learning at Netflix - Technology and Operations Management","isPartOf":{"@id":"https:\/\/d3.harvard.edu\/platform-rctom\/#website"},"primaryImageOfPage":{"@id":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/ml-and-chill-machine-learning-at-netflix\/#primaryimage"},"image":{"@id":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/ml-and-chill-machine-learning-at-netflix\/#primaryimage"},"thumbnailUrl":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-content\/uploads\/sites\/4\/2018\/11\/edc0298a-b9a0-11e7-9274-06c476b5c346_aim_1024w-1.png","datePublished":"2018-11-13T22:59:40+00:00","breadcrumb":{"@id":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/ml-and-chill-machine-learning-at-netflix\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/d3.harvard.edu\/platform-rctom\/submission\/ml-and-chill-machine-learning-at-netflix\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/ml-and-chill-machine-learning-at-netflix\/#primaryimage","url":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-content\/uploads\/sites\/4\/2018\/11\/edc0298a-b9a0-11e7-9274-06c476b5c346_aim_1024w-1.png","contentUrl":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-content\/uploads\/sites\/4\/2018\/11\/edc0298a-b9a0-11e7-9274-06c476b5c346_aim_1024w-1.png","width":1024,"height":576},{"@type":"BreadcrumbList","@id":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/ml-and-chill-machine-learning-at-netflix\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/d3.harvard.edu\/platform-rctom\/"},{"@type":"ListItem","position":2,"name":"Submissions","item":"https:\/\/d3.harvard.edu\/platform-rctom\/submission\/"},{"@type":"ListItem","position":3,"name":"ML and Chill: Machine learning at Netflix"}]},{"@type":"WebSite","@id":"https:\/\/d3.harvard.edu\/platform-rctom\/#website","url":"https:\/\/d3.harvard.edu\/platform-rctom\/","name":"Technology and Operations Management","description":"MBA Student Perspectives","potentialAction":[{"@type":"性视界Action","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/d3.harvard.edu\/platform-rctom\/?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-rctom\/wp-json\/wp\/v2\/hck-submission\/34254","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/hck-submission"}],"about":[{"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/types\/hck-submission"}],"author":[{"embeddable":true,"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/users\/11096"}],"replies":[{"embeddable":true,"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/comments?post=34254"}],"version-history":[{"count":0,"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/hck-submission\/34254\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/media\/34416"}],"wp:attachment":[{"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/media?parent=34254"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/d3.harvard.edu\/platform-rctom\/wp-json\/wp\/v2\/categories?post=34254"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}