Optimizing the best play in basketball using deep learning

• Published in: Journal of sports analytics 2022-02, Vol.8 (1), p.1-7
• Main Authors: Javadpour, Leili, Blakeslee, Jessica, Khazaeli, Mehdi, Schroeder, Pete
• Format: Article
• Language: English
• ISSN: 2215-020X; 2215-0218
• DOI: 10.3233/JSA-200524

In a close game of basketball, victory or defeat can depend on a single shot. Being able to identify the best player and play scenario for a given opponent’s defense can increase the likelihood of victory. Progress in technology has resulted in an increase in the popularity of sports analytics over the last two decades, where data can be used by teams and individuals to their advantage. A popular data analytic technique in sports is deep learning. Deep learning is a branch of machine learning that finds patterns within big data and can predict future decisions. The process relies on a raw dataset for training purposes. It can be utilized in sports by using deep learning to read the data and provide a better understanding of where players can be the most successful. In this study the data used were on division I women’s basketball games of a private university in a conference featuring top 25 teams. Deep learning was applied to optimize the best offensive play in a game scenario for a given set of features. The system is used to predict the play that would lead to the highest probability of a made shot.