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

arXiv: https://arxiv.org/abs/2603.15212 · HTML: https://mlsanity.com/paper/2603.15212/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 43 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [On Layer Normalization in the Transformer Architecture](https://mlsanity.com/paper/2002.04745/) (2020)
- [Transformer Hawkes Process](https://mlsanity.com/paper/2002.09291/) (2020)
- [Actions Speak Louder Than Goals: Valuing Player Actions in Soccer](https://mlsanity.com/paper/1802.07127/) (2018)
- [Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction](https://mlsanity.com/paper/2303.16005/) (2023)
- [A framework for the fine-grained evaluation of the instantaneous expected value of soccer possessions](https://mlsanity.com/paper/2011.09426/) (2020)
- [Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports](https://mlsanity.com/paper/2405.17680/) (2024)
- [Unified Uncertainty-Aware Diffusion for Multi-Agent Trajectory Modeling](https://mlsanity.com/paper/2503.18589/) (2025)
- [Ball Trajectory Inference from Multi-Agent Sports Contexts Using Set Transformer and Hierarchical Bi-LSTM](https://mlsanity.com/paper/2306.08206/) (2023)
- [TranSPORTmer: A Holistic Approach to Trajectory Understanding in Multi-Agent Sports](https://mlsanity.com/paper/2410.17785/) (2024)
- [Player Chemistry: Striving for a Perfectly Balanced Soccer Team](https://mlsanity.com/paper/2003.01712/) (2020)
- [Forecasting Events in Soccer Matches Through Language](https://mlsanity.com/paper/2402.06820/) (2024)
- [JointDiff: Bridging Continuous and Discrete in Multi-Agent Trajectory Generation](https://mlsanity.com/paper/2509.22522/) (2025)
- [TacEleven: generative tactic discovery for football open play](https://mlsanity.com/paper/2511.13326/) (2025)
- [A Foundation Model for Soccer](https://mlsanity.com/paper/2407.14558/) (2024)
- [Transfer Portal: Accurately Forecasting the Impact of a Player Transfer in Soccer](https://mlsanity.com/paper/2201.11533/) (2022)
- [RisingBALLER: A player is a token, a match is a sentence, A path towards a foundational model for football players data analytics](https://mlsanity.com/paper/2410.00943/) (2024)
- [Forecasting the future development in quality and value of professional football players](https://mlsanity.com/paper/2502.07528/) (2025)
- [What If They Took the Shot? A Hierarchical Bayesian Framework for Counterfactual Expected Goals](https://mlsanity.com/paper/2511.23072/) (2025)
- [EventGPT: Capturing Player Impact from Team Action Sequences Using GPT-Based Framework](https://mlsanity.com/paper/2512.17266/) (2025)
- [VERSA: Verified Event Data Format for Reliable Soccer Analytics](https://mlsanity.com/paper/2601.21981/) (2026)

## Built on by (most cited first, 1 of 1)

- [TacticGen: Grounding Adaptable and Scalable Generation of Football Tactics](https://mlsanity.com/paper/2604.18210/) (2026)

## Abstract (arXiv)

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.