{"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/metadata-embeddings-for-user-and-item-cold","title":"Metadata Embeddings for User and Item Cold-start Recommendations","arxiv_id":"1507.08439","date":"2015-07-30","proceeding":null,"authors":["Maciej Kula"],"abstract":"I present a hybrid matrix factorisation model representing users and items as\nlinear combinations of their content features' latent factors. The model\noutperforms both collaborative and content-based models in cold-start or sparse\ninteraction data scenarios (using both user and item metadata), and performs at\nleast as well as a pure collaborative matrix factorisation model where\ninteraction data is abundant. Additionally, feature embeddings produced by the\nmodel encode semantic information in a way reminiscent of word embedding\napproaches, making them useful for a range of related tasks such as tag\nrecommendations.","url_abs":"http://arxiv.org/abs/1507.08439v1","url_pdf":"http://arxiv.org/pdf/1507.08439v1.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":"metadata-embeddings-for-user-and-item-cold","repo_url":"https://github.com/lyst/lightfm-paper","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"metadata-embeddings-for-user-and-item-cold","repo_url":"https://github.com/lyst/lightfm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"metadata-embeddings-for-user-and-item-cold","repo_url":"https://github.com/doheelab/lightfm_experiment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"metadata-embeddings-for-user-and-item-cold","repo_url":"https://github.com/mfumagalli68/lightFM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"tag","task_name":"TAG"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1507.08439","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}