A Data Science Approach for Predicting Soccer Passes Using Positional Data

Data-driven approaches for evaluating tactical team behavior in soccer are nowadays a widespread method in sport analytics. The large amount of data collections enables experts to generate a deep tactical understanding and extract valuable measurements out of team-performances. However, these approaches are often limited in their comprehensibility and applicability for domain experts. Additionally, defensive behaviour in soccer is notoriously difficult to measure and has been receiving less attention in research and practice compared to measuring offensive performance. The motivation of this research is the design, implementation and validation of data science algorithms, that predict tactical motion of defending players after an occurring event of a pass, one of the most common events in soccer matches. The focus is the establishment and validation of different sets of rules, which simulate the movement behavior of the defending team, based on domain knowledge. The approach provides a high level of applicability for domain experts, in order to use and combine variable predefined rules for prediction, simulation and evaluation of different tactical approaches of defensive behavior.