OpenSTARLab provides open-source standardized data formats and model packages for soccer analytics, with benchmarks showing LEM 3 best on event prediction and a tunable accuracy/reward trade-off in RL.
A Foundation Model for Soccer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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.
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
OpenSTARLab: Open Approach for Spatio-Temporal Agent Data Analysis in Soccer
OpenSTARLab provides open-source standardized data formats and model packages for soccer analytics, with benchmarks showing LEM 3 best on event prediction and a tunable accuracy/reward trade-off in RL.