ABSTRACT
Basketball is one of a number of sports which, within the past decade, have seen an explosion in quantitative metrics and methods for evaluating players and teams. However, it is still challenging to evaluate individual off-ball events (e.g., screens, cuts away from the ball etc.) in terms of how they contribute to the success of a possession. In this study, we develop a deep learning framework DeepHoops to process a unique dataset composed of spatio-temporal tracking data from NBA games in order to generate a running stream of predictions on the expected points to be scored as a possession progresses. We frame the problem as a multi-class sequence classification problem in which our model estimates probabilities of terminal actions taken by players (e.g. take field goal, turnover, foul etc.) at each moment of a possession based on a sequence of ball and player court locations preceding the said moment. Each of these terminal actions is associated with an expected point value, which is used to estimate the expected points to be scored. One of the challenges associated with this problem is the high imbalance in the action classes. To solve this problem, we parameterize a downsampling scheme for the training phase. We demonstrate that DeepHoops is well-calibrated, estimating accurately the probabilities of each terminal action and we further showcase the model's capability to evaluate individual actions (potentially off-ball) within a possession that are not captured by boxscore statistics.
Supplemental Material
- Alina Bialkowski, Patrick Lucey, Peter Carr, Yisong Yue, Sridha Sridharan, and Iain Matthews. 2014. Large-scale analysis of soccer matches using spatiotemporal tracking data. In IEEE ICDM . Google ScholarDigital Library
- Glenn W Brier. 1950. Verification of forecasts expressed in terms of probability. Monthey Weather Review , Vol. 78, 1 (1950), 1--3.Google ScholarCross Ref
- Dan Cervone, Luke Bornn, and Kirk Goldsberry. 2016a. NBA Court Realty. In 10th MIT Sloan Sports Analytics Conference .Google Scholar
- Daniel Cervone, Alex D'Amour, Luke Bornn, and Kirk Goldsberry. 2016b. A multiresolution stochastic process model for predicting basketball possession outcomes. J. Amer. Statist. Assoc. , Vol. 111, 514 (2016), 585--599.Google ScholarCross Ref
- Nitesh V Chawla. 2009. Data mining for imbalanced datasets: An overview. In Data mining and knowledge discovery handbook. Springer, 875--886.Google Scholar
- Franccois Chollet et almbox. 2015. Keras. https://keras.io .Google Scholar
- Daniel Daly-Grafstein and Luke Bornn. 2018. Rao-Blackwellizing Field Goal Percentage. arXiv preprint arXiv:1808.04871 (2018).Google Scholar
- Alexander D'Amour, Daniel Cervone, Luke Bornn, and Kirk Goldsberry. 2015. Move or Die: How Ball Movement Creates Open Shots in the NBA.Google Scholar
- Alexander Franks, Andrew Miller, Luke Bornn, and Kirk Goldsberry. 2015a. Counterpoints: Advanced defensive metrics for nba basketball. 9th Annual MIT Sloan Sports Analytics Conference .Google Scholar
- Alexander Franks, Andrew Miller, Luke Bornn, Kirk Goldsberry, et almbox. 2015b. Characterizing the spatial structure of defensive skill in professional basketball. The Annals of Applied Statistics , Vol. 9, 1 (2015), 94--121.Google ScholarCross Ref
- Yarin Gal and Zoubin Ghahramani. 2016. A theoretically grounded application of dropout in recurrent neural networks. In NIPS . Google ScholarDigital Library
- Felix A Gers, Jürgen Schmidhuber, and Fred Cummins. 1999. Learning to forget: Continual prediction with LSTM. (1999).Google Scholar
- Tilmann Gneiting and Adrian E Raftery. 2007. Strictly proper scoring rules, prediction, and estimation. J. Amer. Statist. Assoc. , Vol. 102, 477 (2007), 359--378.Google ScholarCross Ref
- Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning .MIT Press. http://www.deeplearningbook.org. Google ScholarDigital Library
- Alex Graves, Abdel-rahman Mohamed, and Geoffrey Hinton. 2013. Speech recognition with deep recurrent neural networks. In Acoustics, speech and signal processing (icassp), 2013 ieee international conference on. IEEE, 6645--6649.Google ScholarCross Ref
- Mark Harmon, Patrick Lucey, and Diego Klabjan. 2016. Predicting Shot Making in Basketball Learnt from Adversarial Multiagent Trajectories. arXiv preprint arXiv:1609.04849 (2016).Google Scholar
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation , Vol. 9, 8 (1997), 1735--1780. Google ScholarDigital Library
- Yoon Kim. 2014. Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882 (2014).Google Scholar
- Hoang Minh Le, Yisong Yue, Peter A Carr, and Patrick Lucey. 2017. Coordinated Multi-Agent Imitation Learning. In Proceedings of the 34th International Conference on International Conference on Machine Learning (ICML) . Google ScholarDigital Library
- Zach Lowe. 2013. Lights, Cameras, Revolution. http://grantland.com/features/the-toronto-raptors-sportvu-cameras-nba-analytical-revolution/ Retrieved January 24, 2018 fromGoogle Scholar
- Patrick Lucey, Alina Bialkowski, Mathew Monfort, Peter Carr, and Iain Matthews. 2016. quality vs quantity: Improved shot prediction in soccer using strategic features from spatiotemporal data. In 8th MIT Sloan Sports Analytics Conference .Google Scholar
- N. Mehrasa, Y. Zhong, F. Tung, L. Bornn, and G. More. 2018. Deep Learning of Player Trajectory Representations for Team Activity Analysis. In 11th MIT Sloan Sports Analytics Conference .Google Scholar
- Andrew Miller, Luke Bornn, Ryan Adams, and Kirk Goldsberry. 2014. Factorized Point Process Intensities: A Spatial Analysis of Professional. In ICML . Google ScholarDigital Library
- Andrew C Miller and Luke Bornn. 2017. Possession sketches: Mapping nba strategies. In 11th MIT Sloan Sports Analytics Conference .Google Scholar
- Allan H Murphy. 1973. Hedging and skill scores for probability forecasts. Journal of Applied Meteorology , Vol. 12, 1 (1973), 215--223.Google ScholarCross Ref
- Evangelos Papalexakis and Konstantinos Pelechrinis. 2018. tHoops: A Multi-Aspect Analytical Framework for Spatio-Temporal Basketball Data. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM '18). ACM, 10. Google ScholarDigital Library
- Razvan Pascanu, Caglar Gulcehre, Kyunghyun Cho, and Yoshua Bengio. 2013. How to construct deep recurrent neural networks. arXiv preprint arXiv:1312.6026 (2013).Google Scholar
- Paul Power, Hector Ruiz, Xinyu Wei, and Patrick Lucey. 2017. Not All Passes Are Created Equal: Objectively Measuring the Risk and Reward of Passes in Soccer from Tracking Data. In ACM SIGKDD (KDD '17). Google ScholarDigital Library
- Lutz Prechelt. 1998. Early stopping-but when? In Neural Networks: Tricks of the trade . Springer, 55--69. Google ScholarDigital Library
- Thomas Seidl, Aditya Cherukumudi, Andrew Hartnett, Peter Carr, and Patrick Lucey. 2018. Bhostgusters: Realtime Interactive Play Sketching with Synthesized NBA Defenses. (2018).Google Scholar
- Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research , Vol. 15, 1 (2014), 1929--1958. Google ScholarDigital Library
- Kuan-Chieh Wang and Richard Zemel. 2016. Classifying nba offensive plays using neural networks. In Proceedings of MIT Sloan Sports Analytics Conference .Google Scholar
- Yisong Yue, Patrick Lucey, Peter Carr, Alina Bialkowski, and Ian Matthews. 2014. Learning fine-grained spatial models for dynamic sports play prediction. In ICDM . Google ScholarDigital Library
- Y. Zhong, B. Xu, G. Zhou, L. Bornn, and G. Mori. 2018. Move or Die: How Ball Movement Creates Open Shots in the NBA.Google Scholar
Index Terms
- DeepHoops: Evaluating Micro-Actions in Basketball Using Deep Feature Representations of Spatio-Temporal Data
Recommendations
What Happened Next? Using Deep Learning to Value Defensive Actions in Football Event-Data
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data MiningObjectively quantifying the value of player actions in football (soccer) is a challenging problem. To date, studies in football analytics have mainly focused on the attacking side of the game, while there has been less work on event-driven metrics for ...
A Bayesian Approach to In-Game Win Probability in Soccer
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data MiningIn-game win probability models, which provide a sports team's likelihood of winning at each point in a game based on historical observations, are becoming increasingly popular. In baseball, basketball and American football, they have become important ...
Actions Speak Louder than Goals: Valuing Player Actions in Soccer
KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningAssessing the impact of the individual actions performed by soccer players during games is a crucial aspect of the player recruitment process. Unfortunately, most traditional metrics fall short in addressing this task as they either focus on rare ...
Comments