A Machine Learning Framework for Off Ball Defensive Role and Performance Evaluation in Football
This work addresses a domain-specific challenge in sports analytics by providing a novel method for assessing defensive roles in football, though it is incremental as it builds on existing ghosting models.
The authors tackled the problem of evaluating off-ball defensive performance in football by developing a covariate-dependent Hidden Markov Model (CDHMM) for corner kicks, which infers defensive assignments from tracking data and enables interpretable credit attribution and counterfactual analysis.
Evaluating off-ball defensive performance in football is challenging, as traditional metrics do not capture the nuanced coordinated movements that limit opponent action selection and success probabilities. Although widely used possession value models excel at appraising on-ball actions, their application to defense remains limited. Existing counterfactual methods, such as ghosting models, help extend these analyses but often rely on simulating "average" behavior that lacks tactical context. To address this, we introduce a covariate-dependent Hidden Markov Model (CDHMM) tailored to corner kicks, a highly structured aspect of football games. Our label-free model infers time-resolved man-marking and zonal assignments directly from player tracking data. We leverage these assignments to propose a novel framework for defensive credit attribution and a role-conditioned ghosting method for counterfactual analysis of off-ball defensive performance. We show how these contributions provide a interpretable evaluation of defensive contributions against context-aware baselines.