[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-564372-105":53,"doc-detail-564372-en":126},{"code":4,"msg":5,"data":6},0,"success",[7,14,19,24,29,34,39,44,49],{"id":8,"doc_module":9,"doc_module_name":10,"category_name":11,"show_sort_weight":12,"slug":13},11,1,"Template","Presentations",90,"presentations",{"id":15,"doc_module":9,"doc_module_name":10,"category_name":16,"show_sort_weight":17,"slug":18},12,"Resumes",80,"resumes",{"id":20,"doc_module":9,"doc_module_name":10,"category_name":21,"show_sort_weight":22,"slug":23},14,"Invoices",70,"invoices",{"id":25,"doc_module":9,"doc_module_name":10,"category_name":26,"show_sort_weight":27,"slug":28},15,"Posters",60,"posters",{"id":30,"doc_module":9,"doc_module_name":10,"category_name":31,"show_sort_weight":32,"slug":33},16,"Social Media",50,"social-media",{"id":35,"doc_module":9,"doc_module_name":10,"category_name":36,"show_sort_weight":37,"slug":38},17,"Forms",40,"forms",{"id":40,"doc_module":9,"doc_module_name":10,"category_name":41,"show_sort_weight":42,"slug":43},18,"Letters",30,"letters",{"id":45,"doc_module":9,"doc_module_name":10,"category_name":46,"show_sort_weight":47,"slug":48},21,"Paper Templates",5,"papers-templates",{"id":50,"doc_module":9,"doc_module_name":10,"category_name":51,"show_sort_weight":4,"slug":52},158,"General","general-158",{"code":4,"msg":54,"data":55},"ok",{"site_id":56,"language":57,"slug":58,"title":59,"keywords":60,"description":61,"schema_data":62,"social_meta":119,"head_meta":121,"extra_data":123,"updated_unix":125},105,"en","personalized-embedding-based-e-commerce-recommendations-at-ebay","Personalized Embedding-based e-Commerce Recommendations at eBay","","Recommender systems are vital for e-commerce marketplaces, enabling shoppers to find items they need or love among huge catalogs. This paper presents an approach that learns item and user embeddings in a shared vector space to generate personalized recommendations. To reduce the cold-start challenge, item and user representations are computed from content features and multi-modal onsite activity. Offline ablation and evaluation on eBay traffic improve Recall@k versus the Recently-Viewed-Item method, and production deployment plus scalable engineering are described. Initial A/B tests show about a 6% surface-rate gain by serving 90% of listing-page impressions.",{"@graph":63,"@context":118},[64,80,101],{"@type":65,"itemListElement":66},"BreadcrumbList",[67,71,74,77],{"item":68,"name":69,"@type":70,"position":9},"https://docshare.wps.com","Home","ListItem",{"item":72,"name":10,"@type":70,"position":73},"https://docshare.wps.com/template/",2,{"item":75,"name":11,"@type":70,"position":76},"https://docshare.wps.com/template/presentations/",3,{"item":78,"name":59,"@type":70,"position":79},"https://docshare.wps.com/template/personalized-embedding-based-e-commerce-recommendations-at-ebay/564372/",4,{"url":78,"name":59,"@type":81,"image":82,"author":87,"headline":59,"publisher":90,"fileFormat":93,"inLanguage":57,"description":61,"dateModified":94,"datePublished":95,"encodingFormat":93,"isAccessibleForFree":96,"interactionStatistic":97},"DigitalDocument",{"url":83,"@type":84,"width":85,"height":86},"https://docshare.wps.com/thumbnails/personalized-embedding-based-e-commerce-recommendations-at-ebay/564372.png","ImageObject",442,249,{"name":88,"@type":89},"Quinn Holloway","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/pdf","2026-10-26","2026-10-12",true,{"@type":98,"interactionType":99,"userInteractionCount":76},"InteractionCounter",{"@type":100},"ViewAction",{"@type":102,"mainEntity":103},"FAQPage",[104,110,114],{"name":105,"@type":106,"acceptedAnswer":107},"How does the paper generate personalized recommendations at eBay?","Question",{"text":108,"@type":109},"It learns item and user embeddings in the same vector space, using a two-tower deep learning architecture where one tower represents items and the other represents users.","Answer",{"name":111,"@type":106,"acceptedAnswer":112},"What strategy is used to mitigate the cold-start problem?",{"text":113,"@type":109},"Item and user embeddings are computed using content features for items and multi-modal onsite user activity for users, and the training process includes data ablation to improve robustness.",{"name":115,"@type":106,"acceptedAnswer":116},"What performance improvement is reported compared to Recently-Viewed-Item (RVI) and current production?",{"text":117,"@type":109},"Offline evaluation shows improved Recall@k over RVI, and initial A/B test results indicate roughly a 6% increase in surface rate versus the existing production recommendation module for generating recommendations on 90% of listing page impressions.","https://schema.org",{"og:url":78,"og:type":120,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":122,"canonical":78},"index,follow",{"doc_id":124,"site_id":56},564372,1792382367,{"code":4,"msg":5,"data":127},{"doc_id":124,"user_id":128,"nickname":88,"user_avatar":129,"doc_module":9,"category_id":8,"category_name":11,"doc_title":59,"doc_description":61,"doc_content":130,"file_id":131,"file_url":132,"file_type":133,"file_size":134,"view_count":76,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":135,"language":136,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":137,"faqs":138,"seo_title":139,"seo_description":61,"update_tm":140,"read_time":76},2336474466712,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","Personalized Embedding-based e-Commerce Recommendations  \nat eBay  \nTian Wang  \n[twang5@ebay.com](twang5@ebay.com)eBay Inc.  \nYuri M. Brovman  \n[ybrovman@ebay.com](ybrovman@ebay.com)eBay Inc.  \nSriganesh Madhvanath  \n[smadhvanath@ebay.com](smadhvanath@ebay.com)eBay Inc.  \narXiv :2102 .06 156v 1 [ cs .IR] 11 Feb 2021  \nABSTRACT  \nRecommender systems are an essential component of e-commerce marketplaces, helping consumers navigate massive amounts of inventory and find what they need or love. In this paper, we present an approach for generating personalized item recommendations inan e-commerce marketplace by learning to embed items and users in the same vector space. In order to alleviate the considerable cold-start problem present in large marketplaces, item and user embeddings are computed using content features and multi-modal onsite user activity respectively. Data ablation is incorporated into the offline model training process to improve the robustness of the production system. In offline evaluation using a dataset collected from eBay traffic, our approach was able to improve the Recall@k metric over the Recently-Viewed-Item (RVI) method. This approach to generating personalized recommendations has been launched to serve production traffic, and the corresponding scalable engineering architecture is also presented. Initial A/B test results show that compared to the current personalized recommendation module in production, the proposed method increases the surface rate by ∼6% to generate recommendations for 90% of listing page impressions.  \nCCS CONCEPTS  \n• Computing methodologies → Learning from implicit feedback; Neural networks; • Information systems → Personalization; Information retrieval; Recommender systems.  \nKEYWORDS  \ndeep learning, personalization, recommender systems, e-commerce, cold-start  \nACM Reference Format:  \nTian Wang, Yuri M. Brovman, and Sriganesh Madhvanath. 2021. Personalized Embedding-based e-Commerce Recommendations at eBay. In Proceedings of ACM Conference (Conference’17) . ACM, New York, NY, USA, 9 pages. [https://doi.org/10.1145/nnnnnnn.nnnnnnn](https://doi.org/10.1145/nnnnnnn.nnnnnnn)  \n1 INTRODUCTION  \nGenerating product recommendations for users is commonplace in e-commerce marketplaces. The eBay marketplace, with over 1.6 billion live items and over 183 million users, presents a unique set  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions [from permissions@acm.org](from permissions@acm.org).  \nConference’17, July 2017, Washington, DC, USA © 2021 Association for Computing Machinery.  \nACM ISBN 978-x-xxxx-xxxx-x/YY/MM. . . $15.00 [https://doi.org/10.1145/nnnnnnn.nnnnnnn](https://doi.org/10.1145/nnnnnnn.nnnnnnn)  \nFigure 1: Screenshot of an eBay recommendations module where the user has been previously looking at games.  \nof challenges when it comes to generating recommendations. Traditional collaborative filtering and matrix factorization methods [1] produce poor results given the scale and extreme sparsity of eBay’s user-item matrix [12] . With millions of new items listed daily, the cold start problem affects a substantial fraction of the inventory. Furthermore, over half of the live listings are single quantity, that is, they can be purchased by at most one buyer. After being purchased, items are removed from the site, and no longer accessible to users. Consequently, implicit user feedback signals such as clicks and purchases are extremely sparse. In this paper, we describe how we attempt to address","cbCaiixbQoONXQnu","https://ap.wps.com/l/cbCaiixbQoONXQnu","pdf",9725413,9,"English","# Abstract\n# 1 Introduction\n## Recommendation challenges in e-commerce\n## Personalized recommendations without seed item context\n## User profiling via implicit feedback\n# 2 Approach (two-tower embedding model)\n## Learning item and user embeddings","[{\"question\":\"How does the paper generate personalized recommendations at eBay?\",\"answer\":\"It learns item and user embeddings in the same vector space, using a two-tower deep learning architecture where one tower represents items and the other represents users.\"},{\"question\":\"What strategy is used to mitigate the cold-start problem?\",\"answer\":\"Item and user embeddings are computed using content features for items and multi-modal onsite user activity for users, and the training process includes data ablation to improve robustness.\"},{\"question\":\"What performance improvement is reported compared to Recently-Viewed-Item (RVI) and current production?\",\"answer\":\"Offline evaluation shows improved Recall@k over RVI, and initial A/B test results indicate roughly a 6% increase in surface rate versus the existing production recommendation module for generating recommendations on 90% of listing page impressions.\"}]","Personalized Embedding-based e-Commerce Recommendations at eBay | PDF",1791841828]