{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T13:40:08Z","timestamp":1750858808519,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,18]]},"DOI":"10.1145\/3703323.3703731","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T12:03:28Z","timestamp":1750853008000},"page":"252-260","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["RAPID: Reinforcement Adaptive Policy-tuned Insight Determination for Dynamic User Feedback Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1336-2400","authenticated-orcid":false,"given":"Sourav","family":"Prosad","sequence":"first","affiliation":[{"name":"Intuit India Product Development Centre Pvt Ltd., Bangalore, IN"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0382-7059","authenticated-orcid":false,"given":"Vivek","family":"Kundu","sequence":"additional","affiliation":[{"name":"Intuit India Product Development Centre Private Limited, Bangalore, IN"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7537-2044","authenticated-orcid":false,"given":"Arkadeep","family":"Banerjee","sequence":"additional","affiliation":[{"name":"Intuit India Product Development Centre Private Limited, Bangalore, IN"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5818-8494","authenticated-orcid":false,"given":"Sutanoy","family":"Dasgupta","sequence":"additional","affiliation":[{"name":"Intuit India Product Development Centre Private Limited, Bangalore, IN"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6277-945X","authenticated-orcid":false,"given":"Anusha","family":"Mujumdar","sequence":"additional","affiliation":[{"name":"Intuit India Product Development Centre Private Limited, Bangalore, IN"}]}],"member":"320","published-online":{"date-parts":[[2025,6,25]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Gediminas Adomavicius and Alexander Tuzhilin. 2005. Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions. IEEE Transactions on Knowledge and Data Engineering 17 6 (2005) 734\u2013749.","DOI":"10.1109\/TKDE.2005.99"},{"key":"e_1_3_3_1_3_2","unstructured":"Minmin Chen Alex Beutel Paul Covington Sagar Jain Francesco Belletti and Ed\u00a0H. Chi. 2019. Large-Scale Recommendation Systems: From Algorithms to Engineering to Real-Time Platforms. Proc. IEEE 107 11 (2019) 1912\u20131935."},{"key":"e_1_3_3_1_4_2","first-page":"1205","volume-title":"Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM)","author":"Chen Shuqing","year":"2018","unstructured":"Shuqing Chen, Guanjie Zheng, Dawei Yin, Jiajun Zhou, and Yi Chang. 2018. Stabilizing Reinforcement Learning-Based Recommendation with Double Q-Learning. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM). 1205\u20131214."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3314037"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Xiangnan He Hanwang Zhang Min-Yen Kan and Tat-Seng Chua. 2016. Fast Matrix Factorization for Online Recommendation with Implicit Feedback. Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval (2016) 549\u2013558.","DOI":"10.1145\/2911451.2911489"},{"key":"e_1_3_3_1_7_2","unstructured":"Steven Kapturowski Georg Ostrovski Will\u00a0Dabney Quan Remi Munos and Volodymyr Mnih. 2019. Recurrent experience replay in distributed reinforcement learning. arXiv preprint arXiv:1806.00187 (2019)."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Yehuda Koren Robert Bell and Chris Volinsky. 2009. Matrix factorization techniques for recommender systems. Computer 42 8 (2009) 30\u201337.","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_3_1_9_2","unstructured":"Hongwei Liu Huaxiu Liu Jie Tang Yusheng Wu Zhiqiang Li and Yongfeng Zhang. 2020. End-to-End Deep Reinforcement Learning based Recommendation System with an Interactive Feedback Loop. ACM Transactions on Information Systems (TOIS) 38 2 (2020) 11:1\u201311:28."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei\u00a0A Rusu Joel Veness Marc\u00a0G Bellemare Alex Graves Martin Riedmiller Andreas\u00a0K Fidjeland Georg Ostrovski et\u00a0al. 2015. Human-level control through deep reinforcement learning. Nature 518 7540 (2015) 529\u2013533.","DOI":"10.1038\/nature14236"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Christoph Raab Moritz Heusinger and Frank-Michael Schleif. 2020. Reactive soft prototype computing for concept drift streams. Neurocomputing 416 (2020) 340\u2013351.","DOI":"10.1016\/j.neucom.2019.11.111"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Steffen Rendle. 2012. Factorization Machines with libFM. ACM Transactions on Intelligent Systems and Technology (TIST) 3 3 (2012) 57:1\u201357:22.","DOI":"10.1145\/2168752.2168771"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Daniel\u00a0J Russo Benjamin Van\u00a0Roy Abbas Kazerouni Ian Osband Zheng Wen et\u00a0al. 2018. A tutorial on thompson sampling. Foundations and Trends\u00ae in Machine Learning 11 1 (2018) 1\u201396.","DOI":"10.1561\/2200000070"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/371920.372071"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"David Silver Aja Huang Chris\u00a0J Maddison Arthur Guez Laurent Sifre George van\u00a0den Driessche Julian Schrittwieser Ioannis Antonoglou Veda Panneershelvam Marc Lanctot et\u00a0al. 2016. Mastering the game of Go with deep neural networks and tree search. Nature 529 7587 (2016) 484\u2013489.","DOI":"10.1038\/nature16961"},{"key":"e_1_3_3_1_16_2","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton Richard\u00a0S","year":"2018","unstructured":"Richard\u00a0S Sutton and Andrew\u00a0G Barto. 2018. Reinforcement Learning: An Introduction. MIT press."},{"key":"e_1_3_3_1_17_2","unstructured":"Georgios Theocharous Yash Chandak Philip\u00a0S Thomas and Frits de Nijs. 2020. Reinforcement learning for strategic recommendations. arXiv preprint arXiv:2009.07346 (2020)."},{"key":"e_1_3_3_1_18_2","first-page":"203","volume-title":"Annual conference on artificial intelligence","author":"Tokic Michel","year":"2010","unstructured":"Michel Tokic. 2010. Adaptive \u03b5 -greedy exploration in reinforcement learning based on value differences. In Annual conference on artificial intelligence. Springer, 203\u2013210."},{"key":"e_1_3_3_1_19_2","unstructured":"Robin Van\u00a0Meteren and Maarten Van\u00a0Someren. 2000. Using content-based filtering for recommendation. Proceedings of the Machine Learning in the New Information Age: MLnet\/ECML2000 Workshop (2000) 47\u201356."},{"key":"e_1_3_3_1_20_2","first-page":"237","volume-title":"Proceedings of the 13th ACM International Conference on Web Search and Data Mining (WSDM)","author":"Wang Chao","year":"2020","unstructured":"Chao Wang, Xiaoxue Zhao, Weinan Zhang, and Jun Wang. 2020. Reinforcement Learning for Real-Time User Feedback in Recommender Systems. In Proceedings of the 13th ACM International Conference on Web Search and Data Mining (WSDM). 237\u2013245."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Ronald\u00a0J Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning 8 (1992) 229\u2013256.","DOI":"10.1007\/BF00992696"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331203"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_3_1_24_2","unstructured":"Xiaofeng Zhao Weinan Zhang Jun Wang and Xiaoxue Li. 2013. Reinforcement Learning for Optimizing Personalized Recommendation. Proceedings of the 22nd International Conference on World Wide Web (WWW) (2013) 439\u2013444."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330668"}],"event":{"name":"CODS-COMAD 2024: 8th International Conference on Data Science and Management of Data (12th ACM IKDD CODS and 30th COMAD)","location":"Jodhpur India","acronym":"CODS-COMAD Dec '24"},"container-title":["Proceedings of the 8th International Conference on Data Science and Management of Data (12th ACM IKDD CODS and 30th COMAD)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3703323.3703731","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T13:05:29Z","timestamp":1750856729000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3703323.3703731"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,18]]},"references-count":25,"alternative-id":["10.1145\/3703323.3703731","10.1145\/3703323"],"URL":"https:\/\/doi.org\/10.1145\/3703323.3703731","relation":{},"subject":[],"published":{"date-parts":[[2024,12,18]]},"assertion":[{"value":"2025-06-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}