{"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/inferring-networks-of-substitutable-and","title":"Inferring Networks of Substitutable and Complementary Products","arxiv_id":"1506.08839","date":"2015-06-29","proceeding":null,"authors":["McAuley Julian","Pandey Rahul","Leskovec Jure"],"abstract":"In a modern recommender system, it is important to understand how products\nrelate to each other. For example, while a user is looking for mobile phones,\nit might make sense to recommend other phones, but once they buy a phone, we\nmight instead want to recommend batteries, cases, or chargers. These two types\nof recommendations are referred to as substitutes and complements: substitutes\nare products that can be purchased instead of each other, while complements are\nproducts that can be purchased in addition to each other.\n  Here we develop a method to infer networks of substitutable and complementary\nproducts. We formulate this as a supervised link prediction task, where we\nlearn the semantics of substitutes and complements from data associated with\nproducts. The primary source of data we use is the text of product reviews,\nthough our method also makes use of features such as ratings, specifications,\nprices, and brands. Methodologically, we build topic models that are trained to\nautomatically discover topics from text that are successful at predicting and\nexplaining such relationships. Experimentally, we evaluate our system on the\nAmazon product catalog, a large dataset consisting of 9 million products, 237\nmillion links, and 144 million reviews.","url_abs":"http://arxiv.org/abs/1506.08839v1","url_pdf":"http://arxiv.org/pdf/1506.08839v1.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":"inferring-networks-of-substitutable-and","repo_url":"https://github.com/snap-stanford/snap","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"inferring-networks-of-substitutable-and","repo_url":"https://github.com/abeermohamed1/recommender-system","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1506.08839","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}