English

A Foundation Model for Soccer

Machine Learning 2024-07-23 v1

Abstract

We propose a foundation model for soccer, which is able to predict subsequent actions in a soccer match from a given input sequence of actions. As a proof of concept, we train a transformer architecture on three seasons of data from a professional soccer league. We quantitatively and qualitatively compare the performance of this transformer architecture to two baseline models: a Markov model and a multi-layer perceptron. Additionally, we discuss potential applications of our model. We provide an open-source implementation of our methods at https://github.com/danielhocevar/Foundation-Model-for-Soccer.

Keywords

Cite

@article{arxiv.2407.14558,
  title  = {A Foundation Model for Soccer},
  author = {Ethan Baron and Daniel Hocevar and Zach Salehe},
  journal= {arXiv preprint arXiv:2407.14558},
  year   = {2024}
}
R2 v1 2026-06-28T17:47:45.508Z