{"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/applying-deep-learning-to-basketball","title":"Applying Deep Learning to Basketball Trajectories","arxiv_id":"1608.03793","date":"2016-08-12","proceeding":null,"authors":["Rajiv Shah","Rob Romijnders"],"abstract":"One of the emerging trends for sports analytics is the growing use of player\nand ball tracking data. A parallel development is deep learning predictive\napproaches that use vast quantities of data with less reliance on feature\nengineering. This paper applies recurrent neural networks in the form of\nsequence modeling to predict whether a three-point shot is successful. The\nmodels are capable of learning the trajectory of a basketball without any\nknowledge of physics. For comparison, a baseline static machine learning model\nwith a full set of features, such as angle and velocity, in addition to the\npositional data is also tested. Using a dataset of over 20,000 three pointers\nfrom NBA SportVu data, the models based simply on sequential positional data\noutperform a static feature rich machine learning model in predicting whether a\nthree-point shot is successful. This suggests deep learning models may offer an\nimprovement to traditional feature based machine learning methods for tracking\ndata.","url_abs":"http://arxiv.org/abs/1608.03793v2","url_pdf":"http://arxiv.org/pdf/1608.03793v2.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":"applying-deep-learning-to-basketball","repo_url":"https://github.com/RobRomijnders/RNN_basketball","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"feature-engineering","task_name":"Feature Engineering"},{"task_slug":"sports-analytics","task_name":"Sports Analytics"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1608.03793","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}