Modeling Matches as Language: A Generative Transformer Approach for Counterfactual Player Valuation in Football
This addresses the problem of contextual player valuation in football, offering a counterfactual simulation approach that is incremental over existing methods.
The paper tackles the challenge of evaluating football player transfers by developing ScoutGPT, a generative model that treats match events as sequential tokens to simulate hypothetical lineups, showing measurable changes in offensive progression and goal probabilities in experiments on K League data.
Evaluating football player transfers is challenging because player actions depend strongly on tactical systems, teammates, and match context. Despite this complexity, recruitment decisions often rely on static statistics and subjective expert judgment, which do not fully account for these contextual factors. This limitation stems largely from the absence of counterfactual simulation mechanisms capable of predicting outcomes in hypothetical scenarios. To address these challenges, we propose ScoutGPT, a generative model that treats football match events as sequential tokens within a language modeling framework. Utilizing a NanoGPT-based Transformer architecture trained on next-token prediction, ScoutGPT learns the dynamics of match event sequences to simulate event sequences under hypothetical lineups, demonstrating superior predictive performance compared to existing baseline models. Leveraging this capability, the model employs Monte Carlo sampling to enable counterfactual simulation, allowing for the assessment of unobserved scenarios. Experiments on K League data show that simulated player transfers lead to measurable changes in offensive progression and goal probabilities, indicating that ScoutGPT captures player-specific impact beyond traditional static metrics.