Analyzing pace-of-play in soccer using spatio-temporal event data

Abstract

Pace-of-play is an important characteristic in soccer that can influence the style and outcome of a match. Using event data provided by Wyscout covering one season of regular-season games from five European soccer leagues, we develop four velocity-based pace metrics and examine how pace varies across the pitch, between different leagues, and between different teams. Our findings show that although pace varies considerably, it is generally highest in the offensive third of the pitch, relatively consistent across leagues, and increases with decreasing team quality. Using hierarchical logistic models, we also assess whether the pace metrics are useful in predicting the outcome of a match by constructing models with and without the metrics. We find that the pace variables are statistically significant but only slightly improve the predictive accuracy metrics.