Predicting Shot Making in Basketball Learnt from Adversarial Multiagent Trajectories

Authors: Mark Harmon, Abdolghani Ebrahimi, Patrick Lucey, Diego Klabjan

Abstract:

In this paper, we predict the likelihood of a player making a shot in basketball from multiagent trajectories. To approach this problem, we present a convolutional neural network (CNN) approach where we initially represent the multiagent behavior as an image. To encode the adversarial nature of basketball, we use a multichannel image which we then feed into a CNN. Additionally, to capture the temporal aspect of the trajectories we use “fading.” We find that this approach is superior to a traditional FFN model. By using gradient ascent, we were able to discover what the CNN filters look for during training. Last, we find that a combined FFN+CNN is the best performing network with an error rate of 39%.

Keywords: basketball, computer vision, image processing, convolutional neural network

References:

[1] Sergey Ioffe and Christian Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Interna-tional Conference on Machine Learning, pages 448–456, 2015.
[2] Patrick Lucey, Alina Bialkowski, Peter Carr, Stuart Morgan, Iain Matthews, and Yaser Sheikh. Representing and discovering adversarial team behaviors using player roles. In Proceedings of the IEEE Confer-ence on Computer Vision and Pattern Recognition, pages 2706–2713, 2013.
[3] Bernard Loeffelholz, Earl Bednar, Kenneth W Bauer, et al. Predicting NBA games using neural networks. Journal of Quantitative Analysis in Sports, 5(1):1–15, 2009.
[4] Alan McCabe and Jarrod Trevathan. Artificial intelligence in sports prediction. In Information Technology: New Generations, 2008. Fifth International Conference on, pages 1194–1197. IEEE, 2008.
[5] E. Nalisnick. Predicting basketball shot outcomes. https://enalisnick. wordpress.com/2014/11/24/predicting-basketball-shot-outcomes/, 2014.
[6] Max Murakami-Moses. Analysis of machine learning models predicting basketball shot success.
[7] Kou-Yuan Huang and Wen-Lung Chang. A neural network method for prediction of 2006 world cup football game. In Neural Networks, The International Joint Conference on, pages 1–8. IEEE, 2010.
[8] Kasun Wickramaratna, Min Chen, Shu-Ching Chen, and Mei-Ling Shyu. Neural network based framework for goal event detection in soccer videos. In Multimedia, IEEE International Symposium on, pages 8–pp. IEEE, 2005.
[9] Patrick Lucey, Alina Bialkowski, Peter Carr, Yisong Yue, and Iain Matthews. How to get an open shot: analyzing team movement in basketball using tracking data. MIT SSAC, 2014.
[10] Xinyu Wei, Long Sha, Patrick Lucey, Peter Carr, Sridha Sridharan, and Iain Matthews. Predicting ball ownership in basketball from a monocular view using only player trajectories. In Proceedings of the IEEE International Conference on Computer Vision Workshops, pages 63–70, 2015.
[11] Yisong Yue, Patrick Lucey, Peter Carr, Alina Bialkowski, and Iain Matthews. Learning fine-grained spatial models for dynamic sports play prediction. In Data Mining, 2014 IEEE International Conference on, pages 670–679. IEEE, 2014.
[12] Andrew Miller, Luke Bornn, Ryan P Adams, and Kirk Goldsberry. Factorized point process intensities: A spatial analysis of professional basketball. In Internation Conference on Machine Learning, pages 235– 243, 2014.
[13] Alexander Franks, Andrew Miller, Luke Bornn, Kirk Goldsberry, et al. Characterizing the spatial structure of defensive skill in professional basketball. The Annals of Applied Statistics, 9(1):94–121, 2015.
[14] Alexander Franks, Andrew Miller, Luke Bornn, and Kirk Goldsberry. Counterpoints: Advanced defensive metrics for NBA basketball. In MIT Sloan Sports Analytics Conference, Boston, MA, 2015.
[15] Matej Perse,ˇ Matej Kristan, Stanislav Kovaciˇc,ˇ Goran Vuckoviˇc,ˇ and Janez Persˇ. A trajectory-based analysis of coordinated team activity in a basketball game. Computer Vision and Image Understanding, 113(5):612–621, 2009.
[16] K-c Wang and Richard Zemel. Classifying NBA offensive plays using neural networks. In MIT Sloan Sports Analytics Conference, Boston, MA, 2016.
[17] Daniel Cervone, Alex D’Amour, Luke Bornn, and Kirk Goldsberry. A multiresolution stochastic process model for predicting basketball possession outcomes. Journal of the American Statistical Association, 111(514):585–599, 2016.
[18] Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron C Courville, Ruslan Salakhutdinov, Richard S Zemel, and Yoshua Bengio. Show, attend and tell: Neural image caption generation with visual attention. In ICML, volume 14, pages 77–81, 2015.
[19] Andrej Karpathy and Li Fei-Fei. Deep visual-semantic alignments for generating image descriptions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3128–3137, 2015.
[20] Richard Socher, Andrej Karpathy, Quoc V Le, Christopher D Manning, and Andrew Y Ng. Grounded compositional semantics for finding and describing images with sentences. Transactions of the Association for Computational Linguistics, 2:207–218, 2014.
[21] Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan. Show and tell: A neural image caption generator. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3156–3164, 2015.
[22] Junhua Mao, Wei Xu, Yi Yang, Jiang Wang, Zhiheng Huang, and Alan Yuille. Deep captioning with multimodal recurrent neural networks (m-rnn). In International Conference of Learning Recognition, 2015.
[23] Dumitru Erhan, Yoshua Bengio, Aaron Courville, and Pascal Vincent. Visualizing higher-layer features of a deep network. University of Montreal, 1341:3, 2009.