Taboola Optimizes Artificial Intelligence for Smarter Content Recommendations

Published: 11/21/2017

Last Updated: 11/21/2017

By Michael A Pearce

Hundreds of billions of recommendations to a billion users a month powered by an optimized combination of hardware from Intel and TensorFlow* software

In the world of online, always-on and on-demand media, being slow is the same as not being there at all.

Taboola’s software-as-a-service (SaaS) solution delivers 360 billion content and article recommendations to over a billion unique users every month on thousands of publishers’ sites. Each one is served in a tenth of a second by an artificial intelligence-based (AI) recommendation engine that analyzes contextual information about web visitors and their preferences. Getting this right drives the clicks, views and shares that are the foundation of modern publishing; getting it wrong, or not delivering at all, undermines this key source of revenue and disrupts user experience.

Download complete case study (PDF)

Product and Performance Information

¹

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.

<script>var isTargetEnabled =false;</script>

<script type="text/javascript">
    var cq_tms = {
        wa_emtcontenttype: "emtcontenttype:designanddevelopmentreference/technicalarticle",
        wa_primarycontenttagging: "primarycontenttagging:processors/intelxeonprocessors",
        wa_emtsystemtype: "emtsystemtype:servers",
        wa_emtsubject: "emtsubject:itinformationtechnology/datacenter",
        
        wa_industry_type: "",
        wa_partner_prog: "",
        wa_subject: "",
        wa_biz_size: "",
        wa_emt_org: "",
        wa_emt_intel: "",
        wa_partner_type: "",
        wa_programidentifier: "ude",
        wa_location: "us",
        wa_language: "en",
        wa_english_title: "Taboola Optimizes Artificial Intelligence for Smarter Content Recommendations",
        wa_content_type: "technicalarticle",
        wa_intel_platform: "",
        wa_applications: "",
        wa_local: "en_US",
        wa_intel_technology: "",
        wa_system_type: "",
        wa_product_name: "",
        wa_audience: "emtaudience:business/btssbusinesstechnologysolutionspecialist/developer/softwaredeveloper",
        wa_life_cycle: "",
        wa_cq_url: "/content/www/us/en/developer/articles/technical/taboola-optimizes-artifcial-intelligence-for-smarter-content-recommendations.html",
        wa_page_type_micro: "editorialposttemplate",
        wa_env: "prd",
        wa_cq_pub_env: "publish",
        wa_transl_status: "",
        wa_product_id: "595",
        wa_software: "",
        wa_reference_design: "",
        wa_codename: "",
        wa_created_date: "1633492605418",
        wa_modified_date: "1646859332752",
        wa_off_time: "1694246400000",
        wa_ownedby: "",
        wa_managedby: "",
        wa_idz_nid : "748903",
        wa_event_type: "",
        wa_idz_custom_tags: "",
        wa_programming_language: "",
        wa_skill_level: "",
        wa_solution: "",
        wa_product_formFactor: "",
        wa_operating_system: "",
        wa_marketing_products: "",
        wa_ssg_third_party_prod_sys_sol: "",
        wa_upeNamespace: "",
        wa_doc_id:"",
        wa_doc_version:"",
        wa_doc_publishdate:"",
        
        wa_secondary_content_type: ""
        
        
    };

cq_tms.wa_tms_sync_load = "deferred";
    
    
</script>

<script type="text/javascript">
    var chatContextObj = {};
    chatContextObj["locale"] = 'en-US';
    chatContextObj["app"] = 'SATG';
    chatContextObj["supportProductMap"] = 'NA';
</script>
<script src="/etc.clientlibs/settings/wcm/designs/ver/220720/intel/clientlibs/detect-idsa.min.js" defer></script>

<script type="text/javascript" src="/content/dam/www/global/wap/tms.sync.js" async></script>

<link rel="stylesheet" href="/etc.clientlibs/settings/wcm/designs/ver/220720/intel/clientlibs/pages/commons-page.min.css" type="text/css"><script src="/etc.clientlibs/settings/wcm/designs/ver/220720/intel/clientlibs/pages/commons-page.min.js" defer></script>

<script>!function(){var e=setInterval(function(){"undefined"!=typeof $CQ&&($CQ(function(){CQ_Analytics.SegmentMgr.loadSegments("/etc/segmentation"),CQ_Analytics.ClientContextUtils.init("/etc/clientcontext/intel",window.location.pathname.substr(0,window.location.pathname.indexOf(".")))}),clearInterval(e))},100)}();</script>

<link rel="preload" as="style" href="/etc.clientlibs/settings/wcm/designs/intel/us/en/css/resources/css/intel.rwd.override.css"/>
<link rel="stylesheet" type="text/css" href="/etc.clientlibs/settings/wcm/designs/intel/us/en/css/resources/css/intel.rwd.override.css"/>