Large-Scale In-Game Outcome Forecasting for Match, Team and Players in Football using an Axial Transformer Neural Network

TL;DR

This paper introduces an axial transformer neural network for large-scale, real-time forecasting of multiple in-game actions in football, considering game dynamics, player skills, and interactions for improved tactical and analytical insights.

Contribution

The paper presents a novel axial transformer architecture that efficiently models temporal and player interactions for multi-action prediction in football matches.

Findings

Model makes approximately 75,000 live predictions per game.

The axial transformer performs comparably to regular transformers.

Predictions are consistent and reliable across match timelines.

Abstract

Football (soccer) is a sport that is characterised by complex game play, where players perform a variety of actions, such as passes, shots, tackles, fouls, in order to score goals, and ultimately win matches. Accurately forecasting the total number of each action that each player will complete during a match is desirable for a variety of applications, including tactical decision-making, sports betting, and for television broadcast commentary and analysis. Such predictions must consider the game state, the ability and skill of the players in both teams, the interactions between the players, and the temporal dynamics of the game as it develops. In this paper, we present a transformer-based neural network that jointly and recurrently predicts the expected totals for thirteen individual actions at multiple time-steps during the match, and where predictions are made for each individual player, each team and at the game-level. The neural network is based on an \emph{axial transformer} that efficiently captures the temporal dynamics as the game progresses, and the interactions between the players at each time-step. We present a novel axial transformer design that we show is equivalent to a regular sequential transformer, and the design performs well experimentally. We show empirically that the model can make consistent and reliable predictions, and efficiently makes $\sim$75,000 live predictions at low latency for each game.