Intention Driven Identification of In-Possession Match Phases in Association Football through Temporal Graph Learning
2026-06-08 • Machine Learning
Machine Learning
AI summaryⓘ
The authors developed a new way to identify what football teams are trying to do during the times they have the ball, by looking at detailed tracking data of players. They created a model that breaks down possession into specific phases and intentions, such as attacking or keeping control of the ball. Their AI system, called T-GAN, uses player positions and interactions over time to classify these phases accurately. The model worked well in tests and showed that understanding how players relate to each other and the sequence of actions helps identify phases, especially fast counter-attacks. This approach helps turn raw player movements into meaningful tactical insights.
In-possession phasesSpatiotemporal tracking dataTemporal Graph Attention Network (T-GAN)TransformerFrame-level F1 scoreIntersection over Truth-Dominance (IoT-D)Tactical intentionsPlayer-interaction graphsFootball tacticsMatch phase segmentation
Authors
Yuesen Li, Daniel Link
Abstract
Understanding tactical organisation of association football, hereafter referred to as football, requires identifying distinct match phases. Yet in-possession phases are rarely directly observable and are shaped by evolving tactical intentions, rather than spatial patterns alone. This study proposes a data-driven framework for identifying in-possession match phases from spatiotemporal tracking data. Seven German Bundesliga matches recorded at 25 Hz with TRACAB were analysed. A hierarchical phase model was defined with three tactical intentions (Invade Opponent Space, Keep Possession, Scoring) and six phases (Build Up, Progression, Counter Attack, Maintenance, Sustained Threat, Finishing). A Temporal Graph Attention Network (T-GAN) was developed to combine frame-level player-interaction graphs, contextual features, and Transformer-based temporal modelling. Performance was evaluated using frame-level F1 and a sequence-aware Intersection over Truth-Dominance (IoT-D) metric. T-GAN achieved macro-average frame-level F1 scores of 0.87 at the intention level, 0.76 for invasion-related phases, and 0.79 for scoring phases. At the sequence level, mean diagonal IoT-D F1 increased from 0.68 to 0.79 for intentions and from 0.61 to 0.71 for phases after post-processing, indicating improved temporal coherence. Model comparisons showed that sequence modelling was the main driver of segmentation quality, while graph-based relational modelling was particularly beneficial for Counter Attack recognition. Exploratory player attention analysis further suggested that wide and midfield positional groups contributed strongly to phase discrimination. Overall, the framework translates continuous tracking data into tactically interpretable in-possession phase representations, with potential applications in automated match annotation, tactical analysis, and playing-style profiling.