Glocal Explanations of Expected Goal Models in Soccer

TL;DR

This paper introduces glocal explanation methods for expected goal models in soccer, enabling team and player level insights through aggregated SHAP values and partial dependence profiles, enhancing interpretability and performance analysis.

Contribution

It proposes a novel approach to explain black-box expected goal models at group levels using aggregated SHAP and partial dependence profiles, bridging local and global interpretability.

Findings

Aggregated SHAP values reveal team and player performance factors.

Partial dependence profiles help understand model behavior at group levels.

Real-data applications demonstrate practical usefulness in soccer analytics.

Abstract

The expected goal models have gained popularity, but their interpretability is often limited, especially when trained using black-box methods. Explainable artificial intelligence tools have emerged to enhance model transparency and extract descriptive knowledge for a single observation or for all observations. However, explaining black-box models for a specific group of observations may be more useful in some domains. This paper introduces the glocal explanations (between local and global levels) of the expected goal models to enable performance analysis at the team and player levels by proposing the use of aggregated versions of the SHAP values and partial dependence profiles. This allows knowledge to be extracted from the expected goal model for a player or team rather than just a single shot. In addition, we conducted real-data applications to illustrate the usefulness of aggregated SHAP and aggregated profiles. The paper concludes with remarks on the potential of these explanations for performance analysis in soccer analytics.