{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T22:06:08Z","timestamp":1782857168011,"version":"3.54.5"},"reference-count":35,"publisher":"Association for Computing Machinery (ACM)","issue":"7","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Commun. ACM"],"published-print":{"date-parts":[[2026,7,1]]},"abstract":"<jats:p>\n                    Many studies in recommender systems (RecSys) adopt a general problem definition, that is\n                    <jats:italic toggle=\"yes\">,<\/jats:italic>\n                    to recommend preferred items to users based on past interactions. Such abstraction often lacks the domain-specific nuances necessary for practical deployment. However, models are frequently evaluated using datasets collected from online recommender platforms, which inherently reflect domain or task specificities. In this article, we analyze RecSys task formulations, emphasizing key components such as input-output structures, temporal dynamics, and candidate item selection. All these factors directly impact offline evaluation. We further examine the complexities of user-item interactions, including decision-making costs, multi-step engagements, and unobservable interactions, which may influence model design. Additionally, we explore the balance between task specificity and model generalizability, highlighting how well-defined task formulations serve as the foundation for robust evaluation and effective solution development. By clarifying task definitions and their implications, this work provides a structured perspective on RecSys research. The goal is to help researchers better navigate the field, particularly in understanding specificities of the RecSys tasks and ensuring fair and meaningful evaluations.\n                  <\/jats:p>","DOI":"10.1145\/3793909","type":"journal-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T16:11:16Z","timestamp":1779984676000},"page":"82-90","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Task-Centric Perspective on Recommender Systems"],"prefix":"10.1145","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0764-4258","authenticated-orcid":false,"given":"Aixin","family":"Sun","sequence":"first","affiliation":[{"name":"Nanyang Technological University, College of Computing and Data Science, Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"issue":"6","key":"e_1_3_1_2_2","first-page":"734","article-title":"Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions","volume":"17","author":"Adomavicius G.","year":"2005","unstructured":"Adomavicius, G. and Tuzhilin, A. Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. IEEE TKDE 17, 6 (2005), 734\u2013749.","journal-title":"IEEE TKDE"},{"key":"e_1_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Anderson A. Kumar R. Tomkins A. and Vassilvitskii S. The dynamics of repeat consumption. In\u00a0WWW.\u00a0ACM (2014) 419\u2013430.","DOI":"10.1145\/2566486.2568018"},{"key":"e_1_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Ariannezhad M. et al. ReCANet: A repeat consumption-aware neural network for next basket recommendation in grocery shopping. In SIGIR. ACM\u00a0(2022) \u00a01240\u20131250.","DOI":"10.1145\/3477495.3531708"},{"key":"e_1_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Beel J. Wegmeth L. Michiels L. and Schulz S. Informed Dataset Selection with \u2018Algorithm Performance Spaces\u2019. In ACM RecSys. ACM\u00a0(2024) 1085\u20131090.","DOI":"10.1145\/3640457.3691704"},{"key":"e_1_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Charolois-Pasqua E. et al. A language model-based playlist generation recommender system. In ACM RecSys. ACM\u00a0(2025) 1\u201311.","DOI":"10.1145\/3705328.3748053"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/963770.963772"},{"key":"e_1_3_1_8_2","unstructured":"Higley K. Burke R. Ekstrand M.D. and Knijnenburg B.P. What news recommendation research did (but mostly didn\u2019t) teach us about building a news recommender. In Proceedings of BEYOND 2025 Workshop co-located ACM RecSys. ACM (2025)."},{"key":"e_1_3_1_9_2","unstructured":"Ivanova V. Lashinin O. Ananyeva M. and Kolesnikov S. RecBaselines2023: A new dataset for choosing baselines for recommender models. In Workshop on Bibliometric-enhanced Information Retrieval (CEUR Workshop Proceedings Vol. 3617). CEUR\u00a0(2023) \u00a052\u201365."},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-0716-2197-4_21"},{"issue":"2","key":"e_1_3_1_11_2","article-title":"A survey on intent-aware recommender systems","volume":"3","author":"Jannach D.","year":"2024","unstructured":"Jannach, D. and Zanker, M. A survey on intent-aware recommender systems. TORS 3, 2\u00a0(Dec. 2024),\u00a0Article 23.","journal-title":"TORS"},{"key":"e_1_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Ji Y. Sun A. Zhang J. and Li C. A re-visit of the popularity baseline in recommender systems. In SIGIR. ACM\u00a0(2020) 1749\u20131752.","DOI":"10.1145\/3397271.3401233"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3569930"},{"key":"e_1_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Katz O. Barkan O. Koenigstein N. and Zabari N. Learning to ride a buy-cycle: A hyper-convolutional model for next basket repurchase recommendation. In ACM RecSys. ACM\u00a0(2022) 316\u2013326.","DOI":"10.1145\/3523227.3546763"},{"key":"e_1_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Kleinberg J. M. Mullainathan S. and Raghavan M. The challenge of understanding what users want: Inconsistent preferences and engagement optimization. In ACM Conf. on Economics and Computation.\u00a0ACM (2022).","DOI":"10.1287\/mnsc.2022.03683"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Le H. H. Liu Y. Medlar A. and Glowacka D. Don\u2019t get ahead of yourself: A critical study on data leakage in offline evaluation of sequential recommenders. In ACM RecSys. ACM\u00a0(2025) 1164\u20131168.","DOI":"10.1145\/3705328.3759329"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3631358.3631362"},{"key":"e_1_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Li J. et al. Right tool right job: Recommendation for repeat and exploration consumption in food delivery. In ACM RecSys. ACM\u00a0(2024) 643\u2013653.","DOI":"10.1145\/3640457.3688119"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3696413"},{"key":"e_1_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Liu W. et al. Neural re-ranking in multi-stage recommender systems: A review. In Proceedings of the Thirty-First Intern. Joint Conf. on Artificial Intelligence. IJCAI (2022) 5512\u20135520.","DOI":"10.24963\/ijcai.2022\/771"},{"key":"e_1_3_1_22_2","doi-asserted-by":"crossref","unstructured":"McElfresh D.C. et al. On the generalizability and predictability of recommender systems. In NeurIPS.\u00a0Curran Associates (2022).","DOI":"10.52202\/068431-0319"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-025-41329-w"},{"key":"e_1_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Ploshkin A. et al. Yambda-5B \u2014 A large-scale multi-modal dataset for ranking and retrieval. In ACM RecSys. ACM\u00a0(2025) 894\u2013901.","DOI":"10.1145\/3705328.3748163"},{"key":"e_1_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Quan S. Liu S. Zheng Z. and Wu F. Enhancing repeat-aware recommendation from a temporal-sequential perspective. In CIKM. ACM\u00a0(2023) 2095\u20132105.","DOI":"10.1145\/3583780.3614866"},{"key":"e_1_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Reiter-Haas M. et al. Predicting music relistening behavior using the ACT-R framework. In ACM RecSys. ACM\u00a0(2021) 702\u2013707.","DOI":"10.1145\/3460231.3478846"},{"key":"e_1_3_1_27_2","unstructured":"Rendle S. Freudenthaler C. Gantner Z. and Schmidt-Thieme L. BPR: Bayesian personalized ranking from implicit feedback. In Conf. on Uncertainty in Artificial Intelligence. AUAI Press\u00a0(2009) 452\u2013461."},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-85820-3_1"},{"key":"e_1_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Shehzad F. Ferrari Dacrema M. and Jannach D. A worrying reproducibility study of intent-aware recommendation models. In SIGIR. ACM\u00a0(2025) 3155\u20133164.","DOI":"10.1145\/3726302.3730307"},{"key":"e_1_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Sun A. Take a fresh look at recommender systems from an evaluation standpoint. In SIGIR. ACM\u00a0(2023) 2629\u20132638.","DOI":"10.1145\/3539618.3591931"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663752.3663756"},{"key":"e_1_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Tsukuda K. and Goto M. Explainable recommendation for repeat consumption. In ACM RecSys. ACM\u00a0(2020) 462\u2013467.","DOI":"10.1145\/3383313.3412230"},{"key":"e_1_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Wang C. et al. Modeling item-specific temporal dynamics of repeat consumption for recommender systems. In WWW.\u00a0ACM\u00a0(2019) 1977\u20131987.","DOI":"10.1145\/3308558.3313594"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3556536"},{"key":"e_1_3_1_35_2","unstructured":"Zou K. and Sun A. A survey of real-world recommender Systems: Challenges constraints and industrial perspectives. arXiv (2025); arXiv:2509.06002."},{"key":"e_1_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Zou K. et al. Hesitation and tolerance in recommender systems. In CHI. ACM (2026).","DOI":"10.1145\/3772318.3791865"}],"container-title":["Communications of the ACM"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3793909","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T21:12:45Z","timestamp":1782853965000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3793909"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":35,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7,1]]}},"alternative-id":["10.1145\/3793909"],"URL":"https:\/\/doi.org\/10.1145\/3793909","relation":{},"ISSN":["0001-0782","1557-7317"],"issn-type":[{"value":"0001-0782","type":"print"},{"value":"1557-7317","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]},"assertion":[{"value":"2025-04-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}