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

• URL: http://arxiv.org/abs/2603.15212v1
• Date: Mon, 16 Mar 2026 12:51:33 GMT
• Title: Modeling Matches as Language: A Generative Transformer Approach for Counterfactual Player Valuation in Football
• Abstract summary: ScoutGPT is a generative model that treats football match events as sequential tokens within a language modeling framework.<n>ScoutGPT learns the dynamics of match event sequences to simulate event sequences under hypothetical lineups.<n> Experiments on K League data show that simulated player transfers lead to measurable changes in offensive progression and goal probabilities.
• Score: 5.36551574565267
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• WorldSimProbe: Diagnosing Simulator Faithfulness in Action-Conditioned World Models for Embodied Manipulation [85.15806404962193]
  Action-conditioned world models (ACWMs) promise to provide embodied AI with scalable predictive simulators for planning, policy evaluation, and data generation.<n>We evaluate ACWMs through the observable capabilities expected of physical simulators.<n>WorldSimProbe reveals systematic action-realization degradation across control variation, structured failures in interaction grounding and dynamics.
  arXiv  Detail & Related papers  (2026-08-10T08:48:06Z)
• TacticGen: Grounding Adaptable and Scalable Generation of Football Tactics [60.9005633936196]
  TacticGen is a generative model for adaptable and scalable tactic generation.<n>Training with over 3.3 million events and 100 million tracking frames from top-tier leagues, TacticGen achieves state-of-the-art precision in predicting player trajectories.<n>A case study with football experts confirms that TacticGen generates realistic, strategically valuable tactics.
  arXiv  Detail & Related papers  (2026-04-20T12:57:11Z)
• GenTac: Generative Modeling and Forecasting of Soccer Tactics [66.35532694378146]
  GenTac conceptualizes soccer tactics as a process over continuous multi-player trajectories and discrete semantic events.<n>It supports rich contextual conditioning, including opponent behavior, specific team or league playing styles, and strategic objectives.<n>It can be successfully trained to generalize to other dynamic team sports, including basketball, American football, and ice hockey.
  arXiv  Detail & Related papers  (2026-04-13T17:53:49Z)
• MOTIF: Learning Action Motifs for Few-shot Cross-Embodiment Transfer [55.982504915794514]
  Cross-embodiment policies typically rely on shared-private architectures.<n>We introduce MOTIF for efficient few-shot cross-embodiment transfer.<n>We show that MOTIF significantly outperforms strong baselines in few-shot transfer scenarios.
  arXiv  Detail & Related papers  (2026-02-14T13:21:40Z)
• ScoutGPT: Capturing Player Impact from Team Action Sequences Using GPT-Based Framework [5.36551574565267]
  We introduce EventGPT, a player-conditioned, value-aware next-event prediction model built on a GPT-style autoregressive transformer.<n>Our model treats match play as a sequence of discrete tokens, jointly learning to predict the next on-ball action's type, location, timing, and its estimated residual On-Ball Value.<n>By substituting learned player embeddings into new event sequences, we can simulate how a player's behavioral distribution and value profile would change when placed in a different team or tactical structure.
  arXiv  Detail & Related papers  (2025-12-19T06:30:11Z)
• What-If Analysis of Large Language Models: Explore the Game World Using Proactive Thinking [50.72154186522052]
  Large language models (LLMs) excel at processing information reactively but lack the ability to systemically explore hypothetical futures.<n>We propose WiA-LLM, a new paradigm that equips LLMs with proactive thinking capabilities.<n>We validate WiA-LLM in Honor of Kings, a complex multiplayer game environment.
  arXiv  Detail & Related papers  (2025-09-05T04:05:27Z)
• Player-Team Heterogeneous Interaction Graph Transformer for Soccer Outcome Prediction [8.197004730382396]
  HIGFormer is a novel graph-augmented transformer-based deep learning model for soccer outcome prediction.<n>It captures both fine-grained player dynamics and high-level team interactions.<n>Experiments on the WyScout Open Access dataset, a large-scale real-world soccer dataset, demonstrate that HIGFormer significantly outperforms existing methods in prediction accuracy.
  arXiv  Detail & Related papers  (2025-07-14T06:43:36Z)
• SportsNGEN: Sustained Generation of Realistic Multi-player Sports Gameplay [19.80390059667457]
  We present a transformer decoder based sports simulation engine, SportsNGEN, trained on sports player and ball tracking sequences. By training on a large database of professional tennis tracking data, we demonstrate that simulations produced by SportsNGEN can be used to predict the outcomes of rallies. We show that the model output sampling parameters are crucial to simulation realism and that SportsNGEN is probabilistically well-calibrated to real data.
  arXiv  Detail & Related papers  (2024-02-10T01:16:21Z)
• Estimating Player Performance in Different Contexts Using Fine-tuned Large Events Models [0.7373617024876725]
  This paper introduces an innovative application of Large Event Models (LEMs) in soccer analytics. LEMs predict variables for subsequent events rather than words. We focus on fine-tuning LEMs with the WyScout dataset for the 2017-18 Premier League season.
  arXiv  Detail & Related papers  (2024-02-09T22:47:25Z)
• ShuttleSHAP: A Turn-Based Feature Attribution Approach for Analyzing Forecasting Models in Badminton [52.21869064818728]
  Deep learning approaches for player tactic forecasting in badminton show promising performance partially attributed to effective reasoning about rally-player interactions. We propose a turn-based feature attribution approach, ShuttleSHAP, for analyzing forecasting models in badminton based on variants of Shapley values.
  arXiv  Detail & Related papers  (2023-12-18T05:37:51Z)
• Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation [66.86987509942607]
  We evaluate how such a paradigm should be done in imitation learning. We consider a setting where the pretraining corpus consists of multitask demonstrations. We argue that inverse dynamics modeling is well-suited to this setting.
  arXiv  Detail & Related papers  (2023-05-26T14:40:46Z)
• Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment [72.50906475214457]
  The goal of sequential event prediction is to estimate the next event based on a sequence of historical events. In practice, the next-event prediction models are trained with sequential data collected at one time. We propose a framework with hierarchical branching structures for learning context-specific representations.
  arXiv  Detail & Related papers  (2022-10-24T07:54:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.