{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T14:20:00Z","timestamp":1775571600970,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,1,30]],"date-time":"2019-01-30T00:00:00Z","timestamp":1548806400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100003246","name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["CI-14-25,612.001.551"],"award-info":[{"award-number":["CI-14-25,612.001.551"]}],"id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ahold Delhaize"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,1,30]]},"DOI":"10.1145\/3289600.3290958","type":"proceedings-article","created":{"date-parts":[[2019,3,11]],"date-time":"2019-03-11T12:33:01Z","timestamp":1552307581000},"page":"447-455","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":39,"title":["When People Change their Mind"],"prefix":"10.1145","author":[{"given":"Rolf","family":"Jagerman","sequence":"first","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]},{"given":"Ilya","family":"Markov","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]},{"given":"Maarten","family":"de Rijke","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]}],"member":"320","published-online":{"date-parts":[[2019,1,30]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"The Social Animal","author":"Aronson Elliot","unstructured":"Elliot Aronson . 2008. The Social Animal 10 th ed.). Worth\/Freeman . Elliot Aronson. 2008. The Social Animal 10th ed.). Worth\/Freeman.","edition":"10"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1541-0420.2005.00377.x"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems","volume":"1","author":"Besbes Omar","year":"2014","unstructured":"Omar Besbes , Yonatan Gur , and Assaf Zeevi . 2014 . Stochastic Multi-Armed-Bandit Problem with Non-stationary Rewards . In Proceedings of the 27th International Conference on Neural Information Processing Systems , Vol. 1 . 199--207. Omar Besbes, Yonatan Gur, and Assaf Zeevi. 2014. Stochastic Multi-Armed-Bandit Problem with Non-stationary Rewards. In Proceedings of the 27th International Conference on Neural Information Processing Systems, Vol. 1. 199--207."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2043932.2044016"},{"key":"e_1_3_2_1_5_1","unstructured":"Nicolo Cesa-Bianchi Claudio Gentile and Giovanni Zappella. 2013. A Gang of Bandits. In Advances in Neural Information Processing Systems 26 . 737--745.   Nicolo Cesa-Bianchi Claudio Gentile and Giovanni Zappella. 2013. A Gang of Bandits. In Advances in Neural Information Processing Systems 26 . 737--745."},{"key":"e_1_3_2_1_6_1","volume-title":"Delicious website","unstructured":"Delicious. 2018. Delicious website . http:\/\/www.delicious.com . (2018). Accessed: 2018-08-09. Delicious. 2018. Delicious website. http:\/\/www.delicious.com . (2018). Accessed: 2018-08-09."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498759.1498825"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence","author":"Dud'ik Miroslav","year":"2012","unstructured":"Miroslav Dud'ik , Dumitru Erhan , John Langford , and Lihong Li . 2012 . Sample-efficient Nonstationary Policy Evaluation for Contextual Bandits . Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence (2012), 247--254. Miroslav Dud'ik, Dumitru Erhan, John Langford, and Lihong Li. 2012. Sample-efficient Nonstationary Policy Evaluation for Contextual Bandits. Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence (2012), 247--254."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 28th International Conference on International Conference on Machine Learning","author":"Dud'ik Miroslav","year":"2011","unstructured":"Miroslav Dud'ik , John Langford , and Lihong Li . 2011 . Doubly Robust Policy Evaluation and Learning . Proceedings of the 28th International Conference on International Conference on Machine Learning (2011), 1097--1104. Miroslav Dud'ik, John Langford, and Lihong Li. 2011. Doubly Robust Policy Evaluation and Learning. Proceedings of the 28th International Conference on International Conference on Machine Learning (2011), 1097--1104."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/2050345.2050365"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2433396.2433419"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1952.10483446"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3239575"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/775047.775067"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Daniel Kahneman Paul Slovic and Amos Tversky (Eds.). 1982. Judgment Under Uncertainty: Heuristics and Biases .Cambridge University Press.  Daniel Kahneman Paul Slovic and Amos Tversky (Eds.). 1982. Judgment Under Uncertainty: Heuristics and Biases .Cambridge University Press.","DOI":"10.1017\/CBO9780511809477"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1935826.1935862"},{"key":"e_1_3_2_1_17_1","unstructured":"Last.fm. 2018. Last.fm website. http:\/\/www.lastfm.com . (2018). Accessed: 2018-08-09.  Last.fm. 2018. Last.fm website. http:\/\/www.lastfm.com . (2018). Accessed: 2018-08-09."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661829.2661947"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1935826.1935878"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11746"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1719970.1719976"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 14th International Society for Music Information Retrieval Conference . 401--406","author":"Moore Joshua L","year":"2013","unstructured":"Joshua L Moore , Shuo Chen , Douglas Turnbull , and Thorsten Joachims . 2013 . Taste Over Time: The Temporal Dynamics of User Preferences . In Proceedings of the 14th International Society for Music Information Retrieval Conference . 401--406 . Joshua L Moore, Shuo Chen, Douglas Turnbull, and Thorsten Joachims. 2013. Taste Over Time: The Temporal Dynamics of User Preferences. In Proceedings of the 14th International Society for Music Information Retrieval Conference . 401--406."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972771.63"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-018-5740-2"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 17th International Conference on Machine Learning. 759--766","author":"Precup Doina","unstructured":"Doina Precup , Richard S. Sutton , and Satinder P. Singh . 2000. Eligibility Traces for Off-Policy Policy Evaluation . In Proceedings of the 17th International Conference on Machine Learning. 759--766 . Doina Precup, Richard S. Sutton, and Satinder P. Singh. 2000. Eligibility Traces for Off-Policy Policy Evaluation. In Proceedings of the 17th International Conference on Machine Learning. 759--766."},{"key":"e_1_3_2_1_28_1","volume-title":"Modeling Musical Taste Evolution with Recurrent Neural Networks. arXiv preprint arXiv:1806.06535","author":"Quadrana Massimo","year":"2018","unstructured":"Massimo Quadrana , Marta Reznakova , Tao Ye , Erik Schmidt , and Hossein Vahabi . 2018. Modeling Musical Taste Evolution with Recurrent Neural Networks. arXiv preprint arXiv:1806.06535 ( 2018 ). Massimo Quadrana, Marta Reznakova, Tao Ye, Erik Schmidt, and Hossein Vahabi. 2018. Modeling Musical Taste Evolution with Recurrent Neural Networks. arXiv preprint arXiv:1806.06535 (2018)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2187836.2187918"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159700"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1080\/14792779143000015"},{"key":"e_1_3_2_1_32_1","volume-title":"Barto","author":"Sutton Richard S.","year":"1998","unstructured":"Richard S. Sutton and Andrew G . Barto . 1998 . Reinforcement Learning : An Introduction .MIT press. Richard S. Sutton and Andrew G. Barto. 1998. Reinforcement Learning: An Introduction .MIT press."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 31st Conference on Neural Information Processing Systems. 3632--3642","author":"Swaminathan Adith","year":"2017","unstructured":"Adith Swaminathan , Akshay Krishnamurthy , Alekh Agarwal , Miro Dudik , John Langford , Damien Jose , and Imed Zitouni . 2017 . Off-policy Evaluation for Slate Recommendation . In Proceedings of the 31st Conference on Neural Information Processing Systems. 3632--3642 . Adith Swaminathan, Akshay Krishnamurthy, Alekh Agarwal, Miro Dudik, John Langford, Damien Jose, and Imed Zitouni. 2017. Off-policy Evaluation for Slate Recommendation. In Proceedings of the 31st Conference on Neural Information Processing Systems. 3632--3642."},{"key":"e_1_3_2_1_34_1","volume-title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning. In Proceedings of the 33rd International Conference on International Conference on Machine Learning","volume":"48","author":"Philip","unstructured":"Philip S. Thomas and Emma Brunskill. 2016 . Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning. In Proceedings of the 33rd International Conference on International Conference on Machine Learning , Vol. 48 . JMLR.org, 2139--2148. Philip S. Thomas and Emma Brunskill. 2016. Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning. In Proceedings of the 33rd International Conference on International Conference on Machine Learning, Vol. 48. JMLR.org, 2139--2148."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/2888116.2888134"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.5555\/3297863.3297882"},{"key":"e_1_3_2_1_37_1","volume-title":"Context Effects on Attitude Responses: The Role of Retrieval and Necessary Structures. Context Effects in Social and Psychological Research","author":"Tourangeau Roger","unstructured":"Roger Tourangeau . 1992. Context Effects on Attitude Responses: The Role of Retrieval and Necessary Structures. Context Effects in Social and Psychological Research , Norbert Schwarz and Seymour Sudman (Eds.). Springer , 35--47. Roger Tourangeau. 1992. Context Effects on Attitude Responses: The Role of Retrieval and Necessary Structures. Context Effects in Social and Psychological Research, Norbert Schwarz and Seymour Sudman (Eds.). Springer, 35--47."},{"key":"e_1_3_2_1_38_1","unstructured":"Dennis Wackerly William Mendenhall and Richard L Scheaffer. 2014. Mathematical Statistics with Applications .Cengage Learning.  Dennis Wackerly William Mendenhall and Richard L Scheaffer. 2014. Mathematical Statistics with Applications .Cengage Learning."},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning. 3589--3597","author":"Wang Yu-Xiang","year":"2017","unstructured":"Yu-Xiang Wang , Alekh Agarwal , and Miroslav Dudik . 2017 . Optimal and Adaptive Off-policy Evaluation in Contextual Bandits . In Proceedings of the 34th International Conference on Machine Learning. 3589--3597 . Yu-Xiang Wang, Alekh Agarwal, and Miroslav Dudik. 2017. Optimal and Adaptive Off-policy Evaluation in Contextual Bandits. In Proceedings of the 34th International Conference on Machine Learning. 3589--3597."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.2307\/3214163"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210051"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2788602"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553524"}],"event":{"name":"WSDM '19: The Twelfth ACM International Conference on Web Search and Data Mining","location":"Melbourne VIC Australia","acronym":"WSDM '19","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3289600.3290958","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3289600.3290958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:02:20Z","timestamp":1750208540000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3289600.3290958"}},"subtitle":["Off-Policy Evaluation in Non-stationary Recommendation Environments"],"short-title":[],"issued":{"date-parts":[[2019,1,30]]},"references-count":42,"alternative-id":["10.1145\/3289600.3290958","10.1145\/3289600"],"URL":"https:\/\/doi.org\/10.1145\/3289600.3290958","relation":{},"subject":[],"published":{"date-parts":[[2019,1,30]]},"assertion":[{"value":"2019-01-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}