{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:10:23Z","timestamp":1757617823153,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,22]]},"DOI":"10.1145\/3705328.3748047","type":"proceedings-article","created":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T10:48:44Z","timestamp":1757155724000},"page":"340-349","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Off-Policy Evaluation and Learning for Matching Markets"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7952-8606","authenticated-orcid":false,"given":"Yudai","family":"Hayashi","sequence":"first","affiliation":[{"name":"Wantedly, inc., Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9656-1420","authenticated-orcid":false,"given":"Shuhei","family":"Goda","sequence":"additional","affiliation":[{"name":"Independent Researcher, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4357-5835","authenticated-orcid":false,"given":"Yuta","family":"Saito","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,9,7]]},"reference":[{"key":"e_1_3_3_3_2_2","unstructured":"Oliver Bembom and Mark\u00a0J van\u00a0der Laan. 2008. Data-adaptive selection of the truncation level for inverse-probability-of-treatment-weighted estimators. (2008)."},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00110"},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"publisher","unstructured":"Miroslav Dud\u00edk Dumitru Erhan John Langford and Lihong Li. 2014. Doubly Robust Policy Evaluation and Optimization. Statist. Sci. 29 4 (2014) 485 \u2013 511. 10.1214\/14-STS500","DOI":"10.1214\/14-STS500"},{"key":"e_1_3_3_3_5_2","unstructured":"Mehrdad Farajtabar Mohammad Ghavamzadeh and Yinlam Chow. 2018. More Robust Doubly Robust Off-policy Evaluation."},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","unstructured":"Jerome\u00a0H. Friedman. 2001. Greedy function approximation: A gradient boosting machine. The Annals of Statistics 29 5 (2001) 1189 \u2013 1232. 10.1214\/aos\/1013203451","DOI":"10.1214\/aos\/1013203451"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159687"},{"key":"e_1_3_3_3_8_2","unstructured":"Shuhei Goda Yudai Hayashi and Yuta Saito. 2024. A Best-of-Both Approach to Improve Match Predictions and Reciprocal Recommendations for Job Search. arxiv:https:\/\/arXiv.org\/abs\/2409.10992\u00a0[cs.IR]"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599783"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474247"},{"key":"e_1_3_3_3_11_2","unstructured":"Joseph\u00a0DY Kang and Joseph\u00a0L Schafer. 2007. Demystifying double robustness: A comparison of alternative strategies for estimating a population mean from incomplete data. (2007)."},{"key":"e_1_3_3_3_12_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Kiyohara Haruka","year":"2024","unstructured":"Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, and Yuta Saito. 2024. Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ycF7mKfVGO"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645343"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240349"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","unstructured":"Kai-Huang Lai Zhe-Rui Yang Pei-Yuan Lai Chang-Dong Wang Mohsen Guizani and Min Chen. 2024. Knowledge-Aware Explainable Reciprocal Recommendation. Proceedings of the AAAI Conference on Artificial Intelligence 38 8 (Mar. 2024) 8636\u20138644. 10.1609\/aaai.v38i8.28708","DOI":"10.1609\/aaai.v38i8.28708"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/2396761.2396770"},{"key":"e_1_3_3_3_17_2","unstructured":"Dawen Liang and Nikos Vlassis. 2022. Local policy improvement for recommender systems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.11431 (2022)."},{"key":"e_1_3_3_3_18_2","unstructured":"Jan\u00a0Malte Lichtenberg Alexander Buchholz Giuseppe Di\u00a0Benedetto Matteo Ruffini and Ben London. 2023. Double clipping: Less-biased variance reduction in off-policy evaluation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.01120 (2023)."},{"key":"e_1_3_3_3_19_2","unstructured":"Ping Liu Haichao Wei Xiaochen Hou Jianqiang Shen Shihai He Kay\u00a0Qianqi Shen Zhujun Chen Fedor Borisyuk Daniel Hewlett Liang Wu Srikant Veeraraghavan Alex Tsun Chengming Jiang and Wenjing Zhang. 2024. LinkSAGE: Optimizing Job Matching Using Graph Neural Networks. arxiv:https:\/\/arXiv.org\/abs\/2402.13430\u00a0[cs.LG]"},{"key":"e_1_3_3_3_20_2","unstructured":"Linhao Luo Liqi Yang Ju Xin Yixiang Fang Xiaofeng Zhang Xiaofei Yang Kai Chen Zhiyuan Zhang and Kai Liu. 2020. RRCN: A Reinforced Random Convolutional Network based Reciprocal Recommendation Approach for Online Dating. arxiv:https:\/\/arXiv.org\/abs\/2011.12586\u00a0[cs.IR]"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3272027"},{"key":"e_1_3_3_3_22_2","volume-title":"Advances in Neural Information Processing Systems","author":"Metelli Alberto\u00a0Maria","year":"2021","unstructured":"Alberto\u00a0Maria Metelli, Alessio Russo, and Marcello Restelli. 2021. Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and Learning. In Advances in Neural Information Processing Systems, A.\u00a0Beygelzimer, Y.\u00a0Dauphin, P.\u00a0Liang, and J.\u00a0Wortman Vaughan (Eds.). https:\/\/openreview.net\/forum?id=_8vCV7AxPZ"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/IIAI-AAI.2013.91"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347026"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"crossref","unstructured":"Iv\u00e1n Palomares Carlos Porcel Luiz Pizzato Ido Guy and Enrique Herrera-Viedma. 2021. Reciprocal Recommender Systems: Analysis of state-of-art literature challenges and opportunities towards social recommendation. Information Fusion 69 (2021) 103\u2013127.","DOI":"10.1016\/j.inffus.2020.12.001"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/1864708.1864747"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645446"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3473320"},{"key":"e_1_3_3_3_29_2","unstructured":"Yuta Saito and Thorsten Joachims. 2022. Off-Policy Evaluation for Large Action Spaces via Embeddings. arxiv:https:\/\/arXiv.org\/abs\/2202.06317\u00a0[cs.LG]"},{"key":"e_1_3_3_3_30_2","first-page":"19089","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Saito Yuta","year":"2022","unstructured":"Yuta Saito and Thorsten Joachims. 2022. Off-Policy Evaluation for Large Action Spaces via Embeddings. In Proceedings of the 39th International Conference on Machine Learning. PMLR, 19089\u201319122."},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3619642"},{"key":"e_1_3_3_3_32_2","series-title":"(ICML\u201923)","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Saito Yuta","year":"2023","unstructured":"Yuta Saito, Qingyang Ren, and Thorsten Joachims. 2023. Off-policy evaluation for large action spaces via conjunct effect modeling. In Proceedings of the 40th International Conference on Machine Learning (Honolulu, Hawaii, USA) (ICML\u201923). JMLR.org, Article 1234, 26\u00a0pages."},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474245"},{"key":"e_1_3_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688099"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511961"},{"key":"e_1_3_3_3_36_2","series-title":"(ICML\u201920)","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Su Yi","year":"2020","unstructured":"Yi Su, Maria Dimakopoulou, Akshay Krishnamurthy, and Miroslav Dud\u00edk. 2020. Doubly robust off-policy evaluation with shrinkage. In Proceedings of the 37th International Conference on Machine Learning(ICML\u201920). JMLR.org, Article 850, 10\u00a0pages."},{"key":"e_1_3_3_3_37_2","series-title":"Proceedings of Machine Learning Research","first-page":"9196","volume-title":"Proceedings of the 37th International Conference on Machine Learning","volume":"119","author":"Su Yi","year":"2020","unstructured":"Yi Su, Pavithra Srinath, and Akshay Krishnamurthy. 2020. Adaptive Estimator Selection for Off-Policy Evaluation. In Proceedings of the 37th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0119), Hal\u00a0Daum\u00e9 III and Aarti Singh (Eds.). PMLR, 9196\u20139205. https:\/\/proceedings.mlr.press\/v119\/su20d.html"},{"key":"e_1_3_3_3_38_2","first-page":"6005","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","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_3_3_39_2","series-title":"Proceedings of Machine Learning Research","first-page":"6005","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","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(Proceedings of Machine Learning Research, Vol.\u00a097), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 6005\u20136014. https:\/\/proceedings.mlr.press\/v97\/su19a.html"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045616"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608774"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3547406"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/2567948.2579240"},{"key":"e_1_3_3_3_44_2","unstructured":"Masatoshi Uehara Chengchun Shi and Nathan Kallus. 2022. A review of off-policy evaluation in reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.06355 (2022)."},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.5555\/3305890.3306052"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/2808797.2809282"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671734"},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"crossref","unstructured":"Ezgi Y\u0131ld\u0131r\u0131m Payam Azad and \u015eule\u00a0G\u00fcnd\u00fcz \u00d6\u011f\u00fcd\u00fcc\u00fc. 2021. biDeepFM: A multi-objective deep factorization machine for reciprocal recommendation. Engineering Science and Technology an International Journal 24 6 (2021) 1467\u20131477.","DOI":"10.1016\/j.jestch.2021.03.010"},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"publisher","unstructured":"Ezgi Y\u0131ld\u0131r\u0131m Payam Azad and \u015eule G\u00fcnd\u00fcz \u00d6\u011f\u00fcd\u00fcc\u00fc. 2021. biDeepFM: A multi-objective deep factorization machine for reciprocal recommendation. Engineering Science and Technology an International Journal 24 6 (2021) 1467\u20131477. 10.1016\/j.jestch.2021.03.010","DOI":"10.1016\/j.jestch.2021.03.010"},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608798"}],"event":{"name":"RecSys '25: Nineteenth ACM Conference on Recommender Systems","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGIR ACM Special Interest Group on Information Retrieval","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Prague Czech Republic","acronym":"RecSys '25"},"container-title":["Proceedings of the Nineteenth ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3705328.3748047","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T11:47:32Z","timestamp":1757159252000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3705328.3748047"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,7]]},"references-count":49,"alternative-id":["10.1145\/3705328.3748047","10.1145\/3705328"],"URL":"https:\/\/doi.org\/10.1145\/3705328.3748047","relation":{},"subject":[],"published":{"date-parts":[[2025,9,7]]},"assertion":[{"value":"2025-09-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}