Memory Augmented Deep Generative Models for Forecasting the Next Shot Location in Tennis

TLDR: In this article, a semi-supervised generative adversarial network (GAN) was proposed to predict shot location and type in tennis players based on their episodic and semantic memory components.

Abstract: 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 behavioral 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.