The soccer game, bit by bit: An information-theoretic analysis

In this article, we present an original method to measure the rate of positional change observed during a soccer match based on the relative spatial distribution of players on the pitch. This is justified as players use their relative position as a key tactical tool to contribute to their team’s objectives. A temporal network representation of the game was used, where nodes are players discretely clustered by physical proximity into disjoint clusters. This study, observational and descriptive in nature, was applied to a set of matches from a major European national football league, with players’ coordinates sampled at 10Hz, resulting in ≈ 60,000 network samples per match. We took an information theoretic approach to measuring the distance between successive samples. Significant correlations were found between measurements and key match events that are empirically known to result in players jostling for position, such as when striving to get unmarked or to mark. These events increase the information distance between samples, while breaks in game play have the opposite effect. Having a measurement of dynamic, structural change in soccer is an original contribution that can complement full match statistical analysis. Hierarchical decomposition of the measurements is possible at multiple levels, building an overall multi-layer map that provides insights into the game dynamics, from the individual player, to the clusters of interacting players, up to the teams and their matches. This comprehensive view of the players’ interacting behavior can be useful for training, tactics and strategy development.