Predicting Shot Making in Basketball Learnt from Adversarial Multiagent Trajectories
This work addresses the problem of improving shot prediction accuracy for basketball analytics, though it is incremental as it builds on existing deep learning methods.
The paper tackles predicting shot-making likelihood in basketball from multiagent trajectories by using a convolutional neural network (CNN) that represents trajectories as images, achieving a 39% error rate with a combined CNN+FFN model.
In this paper, we predict the likelihood of a player making a shot in basketball from multiagent trajectories. Previous approaches to similar problems center on hand-crafting features to capture domain specific knowledge. Although intuitive, recent work in deep learning has shown this approach is prone to missing important predictive features. To circumvent this issue, 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 multi-channel image which we then feed into a CNN. Additionally, to capture the temporal aspect of the trajectories we "fade" the player trajectories. We find that this approach is superior to a traditional FFN model. By using gradient ascent to create images using an already trained CNN, we discover what features the CNN filters learn. Last, we find that a combined CNN+FFN is the best performing network with an error rate of 39%.