{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/billion-scale-commodity-embedding-for-e","title":"Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba","arxiv_id":"1803.02349","date":"2018-03-06","proceeding":"KDD 2018 5","authors":["Jizhe Wang","Pipei Huang","Huan Zhao","Zhibo Zhang","Binqiang Zhao","Dik Lun Lee"],"abstract":"Recommender systems (RSs) have been the most important technology for\nincreasing the business in Taobao, the largest online consumer-to-consumer\n(C2C) platform in China. The billion-scale data in Taobao creates three major\nchallenges to Taobao's RS: scalability, sparsity and cold start. In this paper,\nwe present our technical solutions to address these three challenges. The\nmethods are based on the graph embedding framework. We first construct an item\ngraph from users' behavior history. Each item is then represented as a vector\nusing graph embedding. The item embeddings are employed to compute pairwise\nsimilarities between all items, which are then used in the recommendation\nprocess. To alleviate the sparsity and cold start problems, side information is\nincorporated into the embedding framework. We propose two aggregation methods\nto integrate the embeddings of items and the corresponding side information.\nExperimental results from offline experiments show that methods incorporating\nside information are superior to those that do not. Further, we describe the\nplatform upon which the embedding methods are deployed and the workflow to\nprocess the billion-scale data in Taobao. Using online A/B test, we show that\nthe online Click-Through-Rate (CTRs) are improved comparing to the previous\nrecommendation methods widely used in Taobao, further demonstrating the\neffectiveness and feasibility of our proposed methods in Taobao's live\nproduction environment.","url_abs":"http://arxiv.org/abs/1803.02349v2","url_pdf":"http://arxiv.org/pdf/1803.02349v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"billion-scale-commodity-embedding-for-e","repo_url":"https://github.com/Wang-Yu-Qing/EGES","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"billion-scale-commodity-embedding-for-e","repo_url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/eges","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.02349","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}