{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/everyone-s-a-winner-on-hyperparameter-tuning","title":"Everyone's a Winner! On Hyperparameter Tuning of Recommendation Models","arxiv_id":null,"date":"2023-09-23","proceeding":"Conference 2023 9","authors":["Faisal Shehzad","Dietmar Jannach"],"abstract":"The performance of a recommender system algorithm in terms of common offline accuracy measures often strongly depends on the\r\nchosen hyperparameters. Therefore, when comparing algorithms in offline experiments, we can obtain reliable insights regarding the\r\neffectiveness of a newly proposed algorithm only if we compare it to a number of state-of-the-art baselines that are carefully tuned for\r\neach of the considered datasets. While this fundamental principle of any area of applied machine learning is undisputed, we find that the tuning process for the baselines in the current literature is barely documented in much of today’s published research. Ultimately, in\r\ncase the baselines are actually not carefully tuned, progress may remain unclear. In this paper, we exemplify through a computational\r\nexperiment involving seven recent deep learning models how every method in such an unsound comparison can be reported to be\r\noutperforming the state-of-the-art. Finally, we iterate appropriate research practices to avoid unreliable algorithm comparisons in the\r\nfuture.","url_abs":"https://dl.acm.org/doi/pdf/10.1145/3604915.3609488","url_pdf":"https://dl.acm.org/doi/pdf/10.1145/3604915.3609488","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"everyone-s-a-winner-on-hyperparameter-tuning","repo_url":"https://github.com/Faisalse/RecSys2023_hyperparameter_tuning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"multi-domain-recommender-systems","task_name":"Multi-Domain Recommender Systems"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}