{"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/playerank-data-driven-performance-evaluation","title":"PlayeRank: data-driven performance evaluation and player ranking in soccer via a machine learning approach","arxiv_id":"1802.04987","date":"2018-02-14","proceeding":null,"authors":["Luca Pappalardo","Paolo Cintia","Paolo Ferragina","Emanuele Massucco","Dino Pedreschi","Fosca Giannotti"],"abstract":"The problem of evaluating the performance of soccer players is attracting the\ninterest of many companies and the scientific community, thanks to the\navailability of massive data capturing all the events generated during a match\n(e.g., tackles, passes, shots, etc.). Unfortunately, there is no consolidated\nand widely accepted metric for measuring performance quality in all of its\nfacets. In this paper, we design and implement PlayeRank, a data-driven\nframework that offers a principled multi-dimensional and role-aware evaluation\nof the performance of soccer players. We build our framework by deploying a\nmassive dataset of soccer-logs and consisting of millions of match events\npertaining to four seasons of 18 prominent soccer competitions. By comparing\nPlayeRank to known algorithms for performance evaluation in soccer, and by\nexploiting a dataset of players' evaluations made by professional soccer\nscouts, we show that PlayeRank significantly outperforms the competitors. We\nalso explore the ratings produced by {\\sf PlayeRank} and discover interesting\npatterns about the nature of excellent performances and what distinguishes the\ntop players from the others. At the end, we explore some applications of\nPlayeRank -- i.e. searching players and player versatility --- showing its\nflexibility and efficiency, which makes it worth to be used in the design of a\nscalable platform for soccer analytics.","url_abs":"http://arxiv.org/abs/1802.04987v3","url_pdf":"http://arxiv.org/pdf/1802.04987v3.pdf","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":"playerank-data-driven-performance-evaluation","repo_url":"https://github.com/mesosbrodleto/playerank","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}