Extended xThreat: an explainable quality assessment method for actions in football using game context

Abstract

In the last decade, systematic collection of data is increasingly being used in the world of football which enables the use of mathematics to improve the performance of individual players and teams. The choice for either a xThreat model or a VAEP-like model gives a trade-off between explainability and the ability to take in-game context into account. The main goal of this paper is to create an extended xThreat (expected threat) model that can include game context, thus aiming for explainability while taking into account contextual variables.