Memory Augmented Deep Generative models for Forecasting the Next Shot Location in Tennis
This addresses improving sports analytics for tennis coaches and analysts, but appears incremental as it builds on existing deep learning methods with memory enhancements.
The paper tackles predicting shot location and type in tennis by incorporating neural memory modules to model player memory, achieving results demonstrated on tracking data from the 2012 Australian Open.
This paper presents a novel framework for predicting shot location and type in tennis. Inspired by recent neuroscience discoveries we incorporate neural memory modules to model the episodic and semantic memory components of a tennis player. We propose a Semi Supervised Generative Adversarial Network architecture that couples these memory models with the automatic feature learning power of deep neural networks and demonstrate methodologies for learning player level behavioural patterns with the proposed framework. We evaluate the effectiveness of the proposed model on tennis tracking data from the 2012 Australian Tennis open and exhibit applications of the proposed method in discovering how players adapt their style depending on the match context.