Wide Open Spaces: A statistical technique for measuring space creation in professional soccer


Javier Fernández




Soccer analytics has long focused on the outcomes of discrete, on-ball events; however, much of the sport’s complexity resides in off-ball events. In the words of Johan Cruyff: “it is statistically proven that players actually have the ball 3 minutes on average. So, the most important thing is: what do you do during those 87 minutes when you do not have the ball? That is what determines whether you are a good player or not.” The creation and closure of spaces is a recurrent subject in observation-based tactical analysis, yet it remains highly unexplored from a quantitative perspective.

We present a method for quantifying spatial value occupation and generation during open play. Here direct space occupation refers to space created for oneself, while space generation refers to opening up space for teammates by attracting opponents out of position. We first build a novel parametric pitch con-trol model that incorporates motion information, relative distance to the ball, and player position in order to provide a smooth surface of potential ball control. Through the mixture of all players’ control surfaces we obtain a fuzzy degree of potential ball control at the team level in any given moment. We also con-struct a model for the relative value of any pitch position, based on the position of the ball and using feed forward neural networks. From all this (a player’s invested pitch zones, a team’s pitch control, and the relative value of each zone), we employ the full spatio-temporal dynamics of each player to construct two novel spatial value creation metrics, accounting for both occupation and generation of spaces.

Through the analysis of a first division Spanish league match, we show a handful of approaches to bet-ter understand a missing key factor for performance analysis in soccer: off-ball attacking dynamics. The quantification of space occupation gain and space generation allows us to observe Sergio Busquets’ high relevance during positional attacks through his pivoting skills, the dragging power of Luis Suarez to gen-erate spaces for his teammates, and the capacity of Lionel Messi to occupy spaces of value with smooth movements along the field, among many other characteristics.

The level of detail we can reach with automated quantitative analysis of space dynamics is beyond what can be reached through observational analysis. The capacity of evaluating space occupation and generation opens the door for new research on off-ball dynamics that can be applied in specific matches and situations, and directly integrated into coaches’ analysis. This information can be used not only to better evaluate players’ contributions to their teams, but also to improve their positioning and movement through coaching, providing a key competitive advantage in a complex and dynamic sport.



Building the future of the sports industry