Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Modeling Matches as Language: A Generative Transformer Approach for Counterfactual Player Valuation in Football

Miru Hong, Minho Lee, Geonhee Jo, Hyeokje Jo, Pascal Bauer, Sang-Ki Ko

Abstract

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.

Modeling Matches as Language: A Generative Transformer Approach for Counterfactual Player Valuation in Football

Abstract

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.
Paper Structure (36 sections, 11 equations, 3 figures, 9 tables)

This paper contains 36 sections, 11 equations, 3 figures, 9 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Data-Driven Player Valuation
  4. Generative Modeling of Sports Data
  5. Sequence Modeling for Event Streams
  6. Counterfactual Simulation in Sports
  7. Methodology
  8. Data Representation and Verification
  9. Problem Formulation
  10. Structured Event Tokenization
  11. Context Encoding
  12. Event Encoding
  13. ScoutGPT Architecture
  14. Backbone
  15. Auxiliary Heads for Value Estimation
  16. ...and 21 more sections

Figures (3)

  • Figure 1: Overview of the ScoutGPT framework. Our nanoGPT-based Transformer model autoregressively predicts event tokens, enabling counterfactual 'what-if' simulations. For instance, replacing Kevin De Bruyne with Scott McTominay could alter actions (e.g., pass/shot) or modify the same action with a different location, outcome, or VAEP.
  • Figure 2: Comparison of the mean absolute delta under different numbers of samples. The left shows the per-episode mean absolute delta, while the right shows the cumulative mean absolute delta.
  • Figure 3: $t$-SNE projection of ScoutGPT player embeddings from the 2024 K League season, colored by positional role.