{"id":494,"date":"2016-05-04T10:09:36","date_gmt":"2016-05-04T07:09:36","guid":{"rendered":"http:\/\/kusuaks7\/?p=99"},"modified":"2025-02-26T14:11:10","modified_gmt":"2025-02-26T14:11:10","slug":"demystifying-ad-match-algorithm-at-facebook","status":"publish","type":"post","link":"https:\/\/www.experfy.com\/blog\/consumer-tech\/demystifying-ad-match-algorithm-at-facebook\/","title":{"rendered":"Demystifying Facebook&#8217;s Ad Match Algorithm"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"494\" class=\"elementor elementor-494\" data-elementor-post-type=\"post\">\n\t\t\t\t\t\t<section class=\"has_eae_slider elementor-section elementor-top-section elementor-element elementor-element-5d9dee30 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"5d9dee30\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"has_eae_slider elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-37fd584f\" data-id=\"37fd584f\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-4c90679e elementor-widget elementor-widget-text-editor\" data-id=\"4c90679e\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<strong>Demystifying Facebook&#8217;s Ad Match Algorithm<\/strong>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"has_eae_slider elementor-section elementor-top-section elementor-element elementor-element-46ba337 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"46ba337\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"has_eae_slider elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-f1cf9ac\" data-id=\"f1cf9ac\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-62239db elementor-widget elementor-widget-text-editor\" data-id=\"62239db\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\u201cA breakthrough in Machine Learning would be worth ten Microsofts\u201d is how Bill Gates describes the emerging field of Machine Learning. To give it further context, <a href=\"http:\/\/en.wikipedia.org\/wiki\/Machine_learning\" target=\"_blank\" rel=\"noopener noreferrer\">Machine Learning<\/a> deals with the construction and study of systems that learn from data rather than follow explicitly programmed instructions. In a recent presentation given by Facebook titled \u201c<a href=\"http:\/\/www.slideshare.net\/SessionsEvents\/talk-ewa-dominowska-lessons-from-ml-for-adsmlconference\" target=\"_blank\" rel=\"noopener noreferrer\">Applying Machine Learning to Ads at Facebook Scale<\/a>,\u201d Facebook Machine Learning expert Ewa Dominowska discussed how\u00a0Facebook has strategically applied Machine Learning principles to their Ad Match Algorithm, which has\u00a0made for a better, more effective advertising tool for marketers on the platform.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"has_eae_slider elementor-section elementor-top-section elementor-element elementor-element-b9a5748 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"b9a5748\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"has_eae_slider elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-6e447ff\" data-id=\"6e447ff\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-5f86663 elementor-widget elementor-widget-text-editor\" data-id=\"5f86663\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\tWith over 1\u00a0billion active daily users and 2.5\u00a0million active advertisers on Facebook, matching the right ad with the right user at the right time can be a challenge for marketers looking to connect with consumers on the platform. Additionally, many of these advertisers are creating new ads each day in the same exact\u00a0context as earlier advertisements, so they become\u00a0harder to distinguish and prioritize.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"has_eae_slider elementor-section elementor-top-section elementor-element elementor-element-0bd2a6a elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"0bd2a6a\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"has_eae_slider elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-061633e\" data-id=\"061633e\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-9a77e41 elementor-widget elementor-widget-text-editor\" data-id=\"9a77e41\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\tFacebook addresses this issue, dividing the problem for matching the right users to the\u00a0right ads into two steps based on machine learning methods:\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"has_eae_slider elementor-section elementor-top-section elementor-element elementor-element-89d478d elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"89d478d\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"has_eae_slider elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-da3b9c0\" data-id=\"da3b9c0\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-cc0abcf elementor-widget elementor-widget-text-editor\" data-id=\"cc0abcf\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<ul>\n \t<li><strong>Identify the parameters that factor into making the right match:\u00a0<\/strong>The matching algorithm used by Facebook is based on the concept of decision trees (<a href=\"http:\/\/en.wikipedia.org\/wiki\/Gradient_boosting\" target=\"_blank\" rel=\"noopener noreferrer\">Gradient Boosted Decision Trees<\/a>,\u00a0to be exact), in which specific relevant features are selected to be used as categorical transforms. One of the advantages in using decision trees is that they allow for joint effect modelling of various features (i.e. understanding importance of features based on their behavior) \u2013 a task too cumbersome to be done using only regression methods. Facebook classifies the features used into two categories: contextual features and historical features. Contextual features, as the name suggests, depend exclusively on the current information regarding the context in which the ad is to be shown, such as local time, day of week, device used by the users, current page, etc. Historical features, on the other hand, depend on the knowledge learned\u00a0from previous interactions with the ad or the user such as CTR of the ad, average CTR of the user, and cumulative number of clicks (and several other features that Facebook doesn\u2019t disclose). Based on the studies run by Facebook, historical features by far outweigh contextual features in predicting clicks on ad except when the historical features are not known.<\/li>\n<\/ul>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"has_eae_slider elementor-section elementor-top-section elementor-element elementor-element-9d708b6 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"9d708b6\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"has_eae_slider elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-c4952ca\" data-id=\"c4952ca\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-b552201 elementor-widget elementor-widget-text-editor\" data-id=\"b552201\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<ul>\n \t<li><strong>Keep the matching algorithm fresh by continuously training the algorithm:\u00a0<\/strong>Once the relevant features have been identified, Facebook then uses a regression model to dynamically assign weights to these features. Facebook employs this dual-pronged strategy because it is easier and faster to train a regression model on a continuous basis in order to keep the matching algorithm\u00a0relevant.<\/li>\n<\/ul>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"has_eae_slider elementor-section elementor-top-section elementor-element elementor-element-dfe5ba5 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"dfe5ba5\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"has_eae_slider elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-f6bd40c\" data-id=\"f6bd40c\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-5b52fe5 elementor-widget elementor-widget-text-editor\" data-id=\"5b52fe5\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<strong>How Marketers Leverage This Information:<\/strong>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"has_eae_slider elementor-section elementor-top-section elementor-element elementor-element-7f08609 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"7f08609\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"has_eae_slider elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-5767816\" data-id=\"5767816\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-6b86ae7 elementor-widget elementor-widget-text-editor\" data-id=\"6b86ae7\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\tIn today\u2019s data-driven world, understanding the mechanics of a black box on at least a\u00a0high level can provide marketers a substantial edge. Below are some of the specific ways in which marketers can make best use of the information mentioned above.\n<ol>\n \t<li><strong>Use Facebook\u2019s Automatic Bid Optimization Option:<\/strong> Unless there is a strong reason not to, marketers should use Facebook\u2019s automatic bid optimization option regardless of their payment strategy (CPC, CPM, OCPM or CPA). Based on inner workings of Facebook\u2019s ad matching algorithm, this option is likely to deliver higher quality clicks, greater reach, and a better CTR for their campaign.<\/li>\n \t<li><strong>Provide Accurate Target Audience Information:<\/strong> It is important for marketers to ensure that all adverts within an advert set share the same audience and bid type \u2013 and then allow\u00a0Facebook\u2019s ad match algorithm to optimize for the best performing advert. Since the algorithm takes into consideration the preferences specified by marketers, it is essential that marketers provide accurate information about the target audience. In addition to selecting the audience based on interests and demographics, Facebook provides a couple of options for marketers to further optimize the target audience \u2013 namely, the &#8220;Custom Audience&#8221; and &#8220;Lookalike Audience&#8221; tools through their <a href=\"https:\/\/www.facebook.com\/ads\/manage\/powereditor\" target=\"_blank\" rel=\"noopener noreferrer\">Power Editor<\/a>. Power editor is bulk ads creation and management tool, tailored specifically for large Facebook advertisers. Custom audiences are made up of people in your audience list that have used the same sign-on email to sign up for a Facebook account. Lookalike audiences are audiences derived by Facebook that share similar interests and demographics as your custom audiences.<\/li>\n \t<li><strong>Ensure Your Campaign is Relevant:<\/strong> Because historical features seem to influence clicks more than the contextual features, marketers should focus their time and energy on making their campaigns more and more relevant for their target audiences.<\/li>\n<\/ol>\n&nbsp;\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"has_eae_slider elementor-section elementor-top-section elementor-element elementor-element-4f21766 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"4f21766\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"has_eae_slider elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-c862d50\" data-id=\"c862d50\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-de55e08 elementor-widget elementor-widget-text-editor\" data-id=\"de55e08\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\tAs social media usage continues to grow, Facebook will likely remain one the most prominent advertising platforms for marketers. And as usage of the Facebook platform continues to grow, Facebook\u2019s Ad Match Algorithm will need to evolve to keep up with changes in the volume, variety, and velocity of ads. Marketers are encouraged to keep themselves abreast of the changes in Facebook\u2019s ad technology\u00a0through their daily interactions with the platform to get the most out of their campaigns.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>How Facebook&#8217;s Ad Matching algorithm works and how marketers can use this knowledge to their advantage.<\/p>\n","protected":false},"author":10,"featured_media":2801,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"content-type":"","footnotes":""},"categories":[196],"tags":[96],"ppma_author":[1608],"class_list":["post-494","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-consumer-tech","tag-marketing"],"authors":[{"term_id":1608,"user_id":10,"is_guest":0,"slug":"amit-dingare","display_name":"Amit Dingare","avatar_url":"https:\/\/secure.gravatar.com\/avatar\/?s=96&d=mm&r=g","user_url":"","last_name":"Dingare","first_name":"Amit","job_title":"","description":"Amit earned his B.S. in Mechanical Engineering from University of Pune, India. After working for few years in the retail industry, Amit enrolled as a full time student at Cornell University and earned his Masters in Business Administration(MBA). After his MBA, Amit worked for a Big Four Management Consulting company managing projects in the Finance, Decision Sciences and Analytics domain for Retail, CPG and Pharmaceutical clients. He currently works for 360i, a top 3 agency on Ad Age&#039;s prestigious A-list since 2013.\n\nIn his spare time, Amit has participated and scored in top 5 percentile in various Kaggle Data Science competitions.&nbsp;"}],"_links":{"self":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts\/494","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/users\/10"}],"replies":[{"embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/comments?post=494"}],"version-history":[{"count":5,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts\/494\/revisions"}],"predecessor-version":[{"id":37312,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts\/494\/revisions\/37312"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/media\/2801"}],"wp:attachment":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/media?parent=494"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/categories?post=494"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/tags?post=494"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/ppma_author?post=494"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}