{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T21:17:40Z","timestamp":1780607860769,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,9,13]],"date-time":"2022-09-13T00:00:00Z","timestamp":1663027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,9,18]]},"DOI":"10.1145\/3523227.3547409","type":"proceedings-article","created":{"date-parts":[[2022,9,13]],"date-time":"2022-09-13T14:13:46Z","timestamp":1663078426000},"page":"654-657","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["CONSEQUENCES \u2014 Causality, Counterfactuals and Sequential Decision-Making for Recommender Systems"],"prefix":"10.1145","author":[{"given":"Olivier","family":"Jeunen","sequence":"first","affiliation":[{"name":"Amazon, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thorsten","family":"Joachims","sequence":"additional","affiliation":[{"name":"Dept. of Computer Science & Dept. of Information Science, Cornell University, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harrie","family":"Oosterhuis","sequence":"additional","affiliation":[{"name":"Radboud University, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuta","family":"Saito","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Cornell University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Flavian","family":"Vasile","sequence":"additional","affiliation":[{"name":"Criteo, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,9,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098155"},{"key":"e_1_3_2_1_2_1","volume-title":"Proc. of the KDD cup and workshop, Vol.\u00a02007","author":"Bennett James","year":"2007","unstructured":"James Bennett, Stan Lanning, 2007. The Netflix prize. In Proc. of the KDD cup and workshop, Vol.\u00a02007. 35."},{"key":"e_1_3_2_1_3_1","volume-title":"The 41st international acm sigir conference on research & development in information retrieval. 405\u2013414.","author":"Biega J","unstructured":"Asia\u00a0J Biega, Krishna\u00a0P Gummadi, and Gerhard Weikum. 2018. Equity of attention: Amortizing individual fairness in rankings. In The 41st international acm sigir conference on research & development in information retrieval. 405\u2013414."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240360"},{"key":"e_1_3_2_1_5_1","volume-title":"Values of User Exploration in Recommender Systems. In Fifteenth ACM Conference on Recommender Systems. 85\u201395","author":"Chen Minmin","year":"2021","unstructured":"Minmin Chen, Yuyan Wang, Can Xu, Ya Le, Mohit Sharma, Lee Richardson, Su-Lin Wu, and Ed Chi. 2021. Values of User Exploration in Recommender Systems. In Fifteenth ACM Conference on Recommender Systems. 85\u201395."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411962"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1214\/14-STS500"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning, Vol.\u00a080","author":"Farajtabar Mehrdad","year":"2018","unstructured":"Mehrdad Farajtabar, Yinlam Chow, and Mohammad Ghavamzadeh. 2018. More Robust Doubly Robust Off-policy Evaluation. In Proceedings of the 35th International Conference on Machine Learning, Vol.\u00a080. PMLR, 1447\u20131456."},{"key":"e_1_3_2_1_9_1","volume-title":"Off-policy risk assessment in contextual bandits. Advances in Neural Information Processing Systems 34","author":"Huang Audrey","year":"2021","unstructured":"Audrey Huang, Liu Leqi, Zachary Lipton, and Kamyar Azizzadenesheli. 2021. Off-policy risk assessment in contextual bandits. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474247"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474248"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403175"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, Vol.\u00a0139","author":"Kallus Nathan","year":"2021","unstructured":"Nathan Kallus, Yuta Saito, and Masatoshi Uehara. 2021. Optimal Off-Policy Evaluation from Multiple Logging Policies. In Proceedings of the 38th International Conference on Machine Learning, Vol.\u00a0139. PMLR, 5247\u20135256."},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics. PMLR, 1243\u20131251","author":"Kallus Nathan","year":"2018","unstructured":"Nathan Kallus and Angela Zhou. 2018. Policy Evaluation and Optimization with Continuous Treatments. In Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics. PMLR, 1243\u20131251."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498380"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220028"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380130"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403229"},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Machine Learning. PMLR, 6987\u20136998","author":"Mladenov Martin","year":"2020","unstructured":"Martin Mladenov, Elliot Creager, Omer Ben-Porat, Kevin Swersky, Richard Zemel, and Craig Boutilier. 2020. Optimizing long-term social welfare in recommender systems: A constrained matching approach. In International Conference on Machine Learning. PMLR, 6987\u20136998."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462830"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441794"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539813.3545137"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412262"},{"key":"e_1_3_2_1_26_1","unstructured":"Yuta Saito Shunsuke Aihara Megumi Matsutani and Yusuke Narita. 2020. Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation. arXiv preprint arXiv:2008.07146(2020)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3473320"},{"key":"e_1_3_2_1_28_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Saito Yuta","year":"2022","unstructured":"Yuta Saito and Thorsten Joachims. 2022. Off-Policy Evaluation for Large Action Spaces via Embeddings. In International Conference on Machine Learning. PMLR, 19089\u201319122."},{"key":"e_1_3_2_1_29_1","volume-title":"Evaluating the Robustness of Off-Policy Evaluation. In Fifteenth ACM Conference on Recommender Systems. 114\u2013123","author":"Saito Yuta","year":"2021","unstructured":"Yuta Saito, Takuma Udagawa, Haruka Kiyohara, Kazuki Mogi, Yusuke Narita, and Kei Tateno. 2021. Evaluating the Robustness of Off-Policy Evaluation. In Fifteenth ACM Conference on Recommender Systems. 114\u2013123."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525762"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220088"},{"key":"e_1_3_2_1_32_1","unstructured":"Ashudeep Singh and Thorsten Joachims. 2019. Policy Learning for Fairness in Ranking. In Advances in Neural Information Processing Systems Vol.\u00a032."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Yi Su Magd Bayoumi and Thorsten Joachims. 2021. Optimizing Rankings for Recommendation in Matching Markets. arXiv preprint arXiv:2106.01941(2021).","DOI":"10.1145\/3485447.3511961"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525788"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning, Vol.\u00a097","author":"Su Yi","year":"2019","unstructured":"Yi Su, Lequn Wang, Michele Santacatterina, and Thorsten Joachims. 2019. Cab: Continuous Adaptive Blending for Policy Evaluation and Learning. In Proceedings of the 36th International Conference on Machine Learning, Vol.\u00a097. PMLR, 6005\u20136014."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.5555\/2789272.2886805"},{"key":"e_1_3_2_1_37_1","unstructured":"Adith Swaminathan and Thorsten Joachims. 2015. The Self-Normalized Estimator for Counterfactual Learning. In Advances in Neural Information Processing Systems Vol.\u00a028. 3231\u20133239."},{"key":"e_1_3_2_1_38_1","unstructured":"Adith Swaminathan Akshay Krishnamurthy Alekh Agarwal Miro Dudik John Langford Damien Jose and Imed Zitouni. 2017. Off-policy Evaluation for Slate Recommendation. In Advances in Neural Information Processing Systems Vol.\u00a030."},{"key":"e_1_3_2_1_39_1","volume-title":"Machine Learning for Healthcare Conference. PMLR, 2\u201335","author":"Tang Shengpu","year":"2021","unstructured":"Shengpu Tang and Jenna Wiens. 2021. Model selection for offline reinforcement learning: Practical considerations for healthcare settings. In Machine Learning for Healthcare Conference. PMLR, 2\u201335."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9541"},{"key":"e_1_3_2_1_41_1","volume-title":"International Conference on Machine Learning. PMLR, 2380\u20132388","author":"Thomas Philip","year":"2015","unstructured":"Philip Thomas, Georgios Theocharous, and Mohammad Ghavamzadeh. 2015. High confidence policy improvement. In International Conference on Machine Learning. PMLR, 2380\u20132388."},{"key":"e_1_3_2_1_42_1","unstructured":"Cameron Voloshin Hoang\u00a0M Le Nan Jiang and Yisong Yue. 2019. Empirical study of off-policy policy evaluation for reinforcement learning. arXiv preprint arXiv:1911.06854(2019)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305890.3306052"}],"event":{"name":"RecSys '22: Sixteenth ACM Conference on Recommender Systems","location":"Seattle WA USA","acronym":"RecSys '22","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 16th ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3523227.3547409","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3523227.3547409","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:03:01Z","timestamp":1750186981000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3523227.3547409"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,13]]},"references-count":41,"alternative-id":["10.1145\/3523227.3547409","10.1145\/3523227"],"URL":"https:\/\/doi.org\/10.1145\/3523227.3547409","relation":{},"subject":[],"published":{"date-parts":[[2022,9,13]]},"assertion":[{"value":"2022-09-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}