{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T22:27:55Z","timestamp":1774909675791,"version":"3.50.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,8]]},"abstract":"<jats:p>Recommendations are commonly used to modify\nuser\u2019s natural behavior, for example, increasing\nproduct sales or the time spent on a website. This\nresults in a gap between the ultimate business ob-\njective and the classical setup where recommenda-\ntions are optimized to be coherent with past user be-\nhavior. To bridge this gap, we propose a new learn-\ning setup for recommendation that optimizes for the\nIncremental Treatment Effect (ITE) of the policy.\nWe show this is equivalent to learning to predict\nrecommendation outcomes under a fully random\nrecommendation policy and propose a new domain\nadaptation algorithm that learns from logged data\ncontaining outcomes from a biased recommenda-\ntion policy and predicts recommendation outcomes\naccording to random exposure. We compare our\nmethod against state-of-the-art factorization meth-\nods, in addition to new approaches of causal rec-\nommendation and show significant improvements.<\/jats:p>","DOI":"10.24963\/ijcai.2019\/870","type":"proceedings-article","created":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:46:05Z","timestamp":1564299965000},"page":"6236-6240","source":"Crossref","is-referenced-by-count":3,"title":["Causal Embeddings for Recommendation: An Extended Abstract"],"prefix":"10.24963","author":[{"given":"Flavian","family":"Vasile","sequence":"first","affiliation":[{"name":"Criteo AI Lab, Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen","family":"Bonner","sequence":"additional","affiliation":[{"name":"Durham University, Durham, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"name":"Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}","theme":"Artificial Intelligence","location":"Macao, China","acronym":"IJCAI-2019","number":"28","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2019,8,10]]},"end":{"date-parts":[[2019,8,16]]}},"container-title":["Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:52:21Z","timestamp":1564300341000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2019\/870"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2019\/870","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}