Evaluating passing decision-making in professional football: An enhanced MPNN approach to Receiver Selection
arXiv:2605.25696v1 Announce Type: new Abstract: The process of decision-making in football is characterized by a complex interplay between spatial positioning, opponent pressure, and player intent. This work introduces a Graph Neural Network (GNN) framework designed to predict Receiver Selection, the optimal passing target, by modeling on-field interactions as dynamic graphs. Each player is represented as a node with positional and contextual features, while potential passing lines form weighted edges characterized by distance, angle, and pressure metrics. A Message-Passing Neural Network (MPN
The increasing sophistication of Graph Neural Networks and their application to complex, dynamic systems like sports is making such analysis feasible.
This work demonstrates an advanced application of AI in analyzing dynamic, multi-agent interactions, which has implications beyond sports for areas requiring real-time decision optimization.
The ability to accurately model and predict optimal decision-making in football through GNNs introduces new analytical tools for strategy development and performance evaluation.
- · Professional sports teams
- · Sports analytics companies
- · Machine learning researchers
- · AI algorithm developers
- · Traditional sports scouting methods
- · Intuition-based coaching approaches
Improved strategic decision-making and player development in professional football.
Expansion of similar GNN applications to other multi-agent, dynamic environments such as logistics or warfare simulation.
Potential for autonomous agent systems to make real-time, complex decisions in dynamic environments, informed by GNN modeling.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG