Blame is easier than praise: Measuring off-ball defensive performance in football
This work provides the first reliable metric for quantifying positioning errors in football, addressing a long-standing gap in player evaluation for analysts and teams.
The paper introduces a framework to measure off-ball defensive performance in football by attributing event-level changes in expected threat to individual defenders using defensive pressure areas and role-conditioned baselines. The method achieves a validity score improved by around 1 standard deviation over the best action-based metric, with 'blame' for conceding high-value actions strongly correlating with external ratings and market values.
The defensive performance of football players is commonly measured through a limited number of actions like tackles and interceptions while their continuous impact through positional behaviour has hardly been studied before. We formulate this problem as an attribution over multi-agent spatiotemporal trajectories without player-level ground truth labels, where event-level changes of expected threat are distributed among individuals. We propose a framework that performs this attribution using player involvement scores calculated from defensive pressure areas (DPAs). By computing role-conditioned baselines within automatically detected team structures, we can determine each defender's expected responsibility for threat created through arbitrary passes. The validity and robustness of this approach are evaluated on a uniquely extensive cross-gender and cross-competition data set, including positional and event data from 64 matches of the men's World Cup, 116 matches of the women's German Bundesliga and 336 matches of the men's German 3. Liga. In the absence of a ground truth, we propose an evaluation protocol that combines multiple relatively weak proxies into robust summary scores. We find a validity score that is improved by around 1 standard deviation compared to the best action-based metric and demonstrate that many popular measures show limited validity. The "blame" for conceding high-value actions shows especially strong correlations with external ratings and market values, making it the first published metric in football to reliably measure positioning errors. All code underlying this work is publicly available to support reproducibility and further research.