Automated Explanation of Machine Learning Models of Footballing Actions in Words
This work addresses the need for actionable insights in football analytics by making model predictions more interpretable for coaches and commentators, though it is incremental as it applies existing methods to a specific domain.
The paper tackled the communication gap between machine learning models and football coaching staff by developing 'wordalizations' that use large language models to generate descriptive sentences from an expected goals model's coefficients, and provided an interactive open-source application for shots in recent tournaments.
While football analytics has changed the way teams and analysts assess performance, there remains a communication gap between machine learning practice and how coaching staff talk about football. Coaches and practitioners require actionable insights, which are not always provided by models. To bridge this gap, we show how to build wordalizations (a novel approach that leverages large language models) for shots in football. Specifically, we first build an expected goals model using logistic regression. We then use the co-efficients of this regression model to write sentences describing how factors (such as distance, angle and defensive pressure) contribute to the model's prediction. Finally, we use large language models to give an entertaining description of the shot. We describe our approach in a model card and provide an interactive open-source application describing shots in recent tournaments. We discuss how shot wordalisations might aid communication in coaching and football commentary, and give a further example of how the same approach can be applied to other actions in football.