What Happened Next? Using Deep Learning to Value Defensive Actions in Football Event-Data

TL;DR

This paper introduces a deep learning-based metric called DAxT to quantify the value of defensive actions in football by assessing the prevented threats, validated on Premier League data.

Contribution

The paper presents a novel deep learning model for valuing defensive actions in football, focusing on threat prevention, which was less explored compared to attacking metrics.

Findings

DAxT effectively predicts the impact of defensive actions.

Model-derived defensive ratings correlate with expert assessments.

The approach improves valuation of defenders using event-data.

Abstract

Objectively quantifying the value of player actions in football (soccer) is a challenging problem. To date, studies in football analytics have mainly focused on the attacking side of the game, while there has been less work on event-driven metrics for valuing defensive actions (e.g., tackles and interceptions). Therefore in this paper, we use deep learning techniques to define a novel metric that values such defensive actions by studying the threat of passages of play that preceded them. By doing so, we are able to value defensive actions based on what they prevented from happening in the game. Our Defensive Action Expected Threat (DAxT) model has been validated using real-world event-data from the 2017/2018 and 2018/2019 English Premier League seasons, and we combine our model outputs with additional features to derive an overall rating of defensive ability for players. Overall, we find that our model is able to predict the impact of defensive actions allowing us to better value defenders using event-data.