Football Analytics: Finding patters in passing behavior

Passing is the backbone of soccer and forms the basis of important decisions made by managers and owners; such as buying players, picking offensive or defensive strategies or even defining a style of play. These decisions can be supported by analyzing how a player performs and how his style affects team performance. The ow of a player or a team can be studied by finding unique patterns in passing (motifs) from the patterns in the subgraphs of a possession-passing network of soccer games.     

These ow motifs can be used to analyze individual players and teams based on the diversity and frequency of their involvement in different motifs. This gives us information about the “style” of a player/team. This style is represented in a unique fashion, as shown in the figure, and can be used to compare players, teams and seasons. Building on the ow motif analyses, an expected goals model can measure the effectiveness of each style of play.

Our data set has the last 4 seasons of 6 big European leagues with 8219 matches, 3532 unique players and 155 unique teams. Flow motifs can be used to analyze different events, for example the transfer of Claudio Bravo to Pep Guardiola’s Manchester City, why is Jean Seri an elite midelder, and the difference in attacking style between Lionel Messi and Cristiano Ronaldo. The paper also analyzes Post-Fàbregas Arsenal wherein different techniques are combined to analyze the impact the acquisition of Mesut Özil and Alexis Sánchez had on the strategies implemented at Arsenal.

This paper was a finalist in the Research Paper Competition at the MIT Sloan Sports Analytics Conference (SSAC). The MIT SSAC is the leading conference for industry professionals, researchers and students to discuss the increasing role of analytics in the global sports industry. You can read the paper here