A Foundation Model for Soccer
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 8 of its 12 references that are in the map. First posted on arXiv 18 Jul 2024.
Builds on
8 of 12 references.
References · 8
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020Scaling Laws for Neural Language Modelscited by 6,411
- 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
- 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
- 2018Actions Speak Louder Than Goals: Valuing Player Actions in Soccercited by 90
- 2020A framework for the fine-grained evaluation of the instantaneous expected value of soccer possessionscited by 24
- 2024Forecasting Events in Soccer Matches Through Languagecited by 5
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.
- 2025OpenSTARLab: Open Approach for Spatio-Temporal Agent Data Analysis in Soccercited by 7
- 2025Beyond Pixels: Leveraging the Language of Soccer to Improve Spatio-Temporal Action Detection in Broadcast Videoscited by 5
- 2026Modeling Matches as Language: A Generative Transformer Approach for Counterfactual Player Valuation in Footballcited by 0
- 2026Modeling Matches as Language: A Generative Transformer Approach for Counterfactual Player Valuation in Football16 Mar 2026
- 2025Beyond Pixels: Leveraging the Language of Soccer to Improve Spatio-Temporal Action Detection in Broadcast Videos14 May 2025
- 2025OpenSTARLab: Open Approach for Spatio-Temporal Agent Data Analysis in Soccer5 Feb 2025