{"id":1212,"date":"2017-11-26T22:02:10","date_gmt":"2017-11-26T21:02:10","guid":{"rendered":"http:\/\/www.sarahmestiri.com\/?p=1212"},"modified":"2017-12-27T14:38:15","modified_gmt":"2017-12-27T13:38:15","slug":"data-natives-berlin-2017-my-talk-building-a-recommender-system-using-collaborative-filtering","status":"publish","type":"post","link":"https:\/\/www.sarahmestiri.com\/index.php\/2017\/11\/26\/data-natives-berlin-2017-my-talk-building-a-recommender-system-using-collaborative-filtering\/","title":{"rendered":"Data Natives Berlin 2017: my talk &#8220;Building a Recommender System using Collaborative Filtering&#8221;"},"content":{"rendered":"<p>I was invited as a speaker in <a href=\"http:\/\/www.datanatives.io\">Data Natives<\/a> 2017 to give a talk on tech trends track and I chose to speak about <strong>Recommender Systems<\/strong> because it&#8217;s a topic that fascinates me. It&#8217;s a topic that&#8217;s changing the way we shop clothes, order food, purchase books and more!<\/p>\n<p>Behind those systems, there is a big whole stuff being done by <strong>machine learning algorithms<\/strong>, analyzing your behavior from your clicks, views, likes, purchases, social network, localization!<\/p>\n<p>One of those famous recommender systems is the one of <strong>Amazon.com<\/strong>. When you\u00a0find sentences like &#8220;<em><strong>Recommended for you, Sarah<\/strong><\/em>&#8221; or &#8220;<em><strong>Frequently bought together<\/strong><\/em>&#8221; or &#8220;<em><strong>C<\/strong><strong>ustomers who bought this item also bought..<\/strong><\/em>&#8221; you are actually coming across outcomes of these machine learning algorithms.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-1213 size-large\" src=\"http:\/\/sarahmestiri.com\/wp-content\/uploads\/2017\/11\/customer-who-bought-this-also-bought-this-1024x327.jpg\" alt=\"\" width=\"640\" height=\"204\" srcset=\"http:\/\/sarahmestiri.com\/wp-content\/uploads\/2017\/11\/customer-who-bought-this-also-bought-this-1024x327.jpg 1024w, http:\/\/sarahmestiri.com\/wp-content\/uploads\/2017\/11\/customer-who-bought-this-also-bought-this-300x96.jpg 300w, http:\/\/sarahmestiri.com\/wp-content\/uploads\/2017\/11\/customer-who-bought-this-also-bought-this-768x245.jpg 768w, http:\/\/sarahmestiri.com\/wp-content\/uploads\/2017\/11\/customer-who-bought-this-also-bought-this.jpg 1327w\" sizes=\"auto, (max-width: 640px) 100vw, 640px\" \/><\/p>\n<p>I know, it seems like&#8230;<br \/>\n<img loading=\"lazy\" decoding=\"async\" class=\"size-medium wp-image-1215 aligncenter\" src=\"http:\/\/sarahmestiri.com\/wp-content\/uploads\/2017\/11\/shutterstock_192399383-350x234-300x201.jpg\" alt=\"\" width=\"300\" height=\"201\" srcset=\"http:\/\/sarahmestiri.com\/wp-content\/uploads\/2017\/11\/shutterstock_192399383-350x234-300x201.jpg 300w, http:\/\/sarahmestiri.com\/wp-content\/uploads\/2017\/11\/shutterstock_192399383-350x234.jpg 350w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/p>\n<p>But it&#8217;s not! and you can do it as well! you can build your own recommender system, you just have to get an answer for <strong>How to start? and what to consider when building it?\u00a0<\/strong>and I came here to help you make your first steps in :).<\/p>\n<p>I stated Amazon as an example because they are leveraging a method called &#8220;Collaborative Filtering&#8221; in their Recommendation Engine. This method is frequently used in recommender systems, it&#8217;s very famous to the point that sometimes people think that &#8220;recommendation engine <strong>=<\/strong> collaborative filtering&#8221; but Recommender Systems are <strong>not the only<\/strong> application of Collaborative Filtering, and recommendation systems can be done using other methods too.<\/p>\n<p>Others like Netflix and Last.fm are using collaborative filtering too, among others..and thanks to that method.<\/p>\n<blockquote><p>&#8220;35% of Amazon.com\u2019s revenue is generated by its recommendation engine&#8221; [<a href=\"https:\/\/www.mckinsey.com\/industries\/retail\/our-insights\/how-retailers-can-keep-up-with-consumers\">source<\/a>]<\/p>\n<p>&#8220;More than 80% of the TV shows people watch on Netflix are discovered through the platform\u2019s recommendation system.&#8221; [<a href=\"http:\/\/www.wired.co.uk\/article\/how-do-netflixs-algorithms-work-machine-learning-helps-to-predict-what-viewers-will-like\">source<\/a>]<\/p><\/blockquote>\n<blockquote><p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-1216\" src=\"http:\/\/sarahmestiri.com\/wp-content\/uploads\/2017\/11\/478514709-iStock-thearter-curtain-630x420.jpg\" alt=\"\" width=\"630\" height=\"420\" srcset=\"http:\/\/sarahmestiri.com\/wp-content\/uploads\/2017\/11\/478514709-iStock-thearter-curtain-630x420.jpg 630w, http:\/\/sarahmestiri.com\/wp-content\/uploads\/2017\/11\/478514709-iStock-thearter-curtain-630x420-300x200.jpg 300w\" sizes=\"auto, (max-width: 630px) 100vw, 630px\" \/><\/p><\/blockquote>\n<p>What do you wait, let&#8217;s pull back the curtain on Recommender System using Collaborative Filtering!<\/p>\n<p>Check my talk slides <a href=\"https:\/\/docs.google.com\/presentation\/d\/1CNuPPrgJCk8uaeCnkyyPNbMto4iTHFhRYRENbJ4ZYYg\/edit?usp=sharing\">here<\/a>.<\/p>\n<p>And if you want to watch a video, here is the <a href=\"https:\/\/youtu.be\/8hTD-XQHuog\" target=\"_blank\" rel=\"noopener noreferrer\">official video<\/a>.<\/p>\n<p>If you have any questions about the topic, don&#8217;t hesitate to\u00a0post a comment and I will be happy to answer!<\/p>\n","protected":false},"excerpt":{"rendered":"<p>I was invited as a speaker in Data Natives 2017 to give a talk on tech trends track and I chose to speak about Recommender Systems because it&#8217;s a topic that fascinates me. It&#8217;s a topic that&#8217;s changing the way we shop clothes, order food, purchase books and more! Behind those systems, there is a [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":1213,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"sfsi_plus_gutenberg_text_before_share":"","sfsi_plus_gutenberg_show_text_before_share":"","sfsi_plus_gutenberg_icon_type":"","sfsi_plus_gutenberg_icon_alignemt":"","sfsi_plus_gutenburg_max_per_row":"","footnotes":""},"categories":[11],"tags":[],"class_list":["post-1212","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-my-activities"],"_links":{"self":[{"href":"https:\/\/www.sarahmestiri.com\/index.php\/wp-json\/wp\/v2\/posts\/1212","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.sarahmestiri.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.sarahmestiri.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.sarahmestiri.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.sarahmestiri.com\/index.php\/wp-json\/wp\/v2\/comments?post=1212"}],"version-history":[{"count":7,"href":"https:\/\/www.sarahmestiri.com\/index.php\/wp-json\/wp\/v2\/posts\/1212\/revisions"}],"predecessor-version":[{"id":1225,"href":"https:\/\/www.sarahmestiri.com\/index.php\/wp-json\/wp\/v2\/posts\/1212\/revisions\/1225"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.sarahmestiri.com\/index.php\/wp-json\/wp\/v2\/media\/1213"}],"wp:attachment":[{"href":"https:\/\/www.sarahmestiri.com\/index.php\/wp-json\/wp\/v2\/media?parent=1212"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.sarahmestiri.com\/index.php\/wp-json\/wp\/v2\/categories?post=1212"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.sarahmestiri.com\/index.php\/wp-json\/wp\/v2\/tags?post=1212"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}