Inferring Player Location in Sports Matches: Multi-Agent Spatial Imputation from Limited Observations

TL;DR

This paper presents a novel method using LSTM and Graph Neural Networks to accurately impute player locations in soccer matches from sparse event data, significantly reducing error and enabling accessible sports analytics.

Contribution

It introduces a multi-agent spatial imputation model that handles non-uniform timesteps and limited observations, improving location prediction accuracy in sports analytics.

Findings

Estimated player locations within ~6.9m accuracy

Reduced error by ~62% compared to baseline

Enables analysis without expensive tracking data

Abstract

Understanding agent behaviour in Multi-Agent Systems (MAS) is an important problem in domains such as autonomous driving, disaster response, and sports analytics. Existing MAS problems typically use uniform timesteps with observations for all agents. In this work, we analyse the problem of agent location imputation, specifically posed in environments with non-uniform timesteps and limited agent observability (~95% missing values). Our approach uses Long Short-Term Memory and Graph Neural Network components to learn temporal and inter-agent patterns to predict the location of all agents at every timestep. We apply this to the domain of football (soccer) by imputing the location of all players in a game from sparse event data (e.g., shots and passes). Our model estimates player locations to within ~6.9m; a ~62% reduction in error from the best performing baseline. This approach facilitates downstream analysis tasks such as player physical metrics, player coverage, and team pitch control. Existing solutions to these tasks often require optical tracking data, which is expensive to obtain and only available to elite clubs. By imputing player locations from easy to obtain event data, we increase the accessibility of downstream tasks.