Abstract
The paper explores process mining and its usefulness for analyzing football event data. We work with professional event data provided by OPTA Sports from the European Championship in 2016. We analyze one game of a favorite team (England) against an underdog team (Iceland). The success of the underdog teams in the Euro 2016 was remarkable, and it is what made the event special. For this reason, it is interesting to compare the performance of a favorite and an underdog team by applying process mining. The goal is to show the options that these types of algorithms and visual analytics offer for the interpretation of event data in football and discuss how the gained insights can support decision makers not only in pre- and post-match analysis but also during live games as well. We show process mining techniques which can be used to gain team or individual player insights by considering the types of actions, the sequence of actions, and the order of player involvement in each sequence. Finally, we also demonstrate the detection of typical or unusual behavior by trace and sequence clustering.
Highlights
Analyzing the tactical behavior in team sports is of paramount importance in sports performance analysis
The main issue, converting the log data into a format required by the process mining algorithms, is that each event in the OPTA log is described over several rows
This paper presents an exploratory study to evaluate the potential and suitability of process mining for tactical football performance analysis
Summary
Analyzing the tactical behavior in team sports is of paramount importance in sports performance analysis. It is possible to detect bottlenecks, monitor the utilization of resources, or predict the remaining processing time of running cases (van der Aalst, 2016) On its own, this perspective will most likely not be too interesting in a football scenario. Process mining is not a reporting, but an analysis tool, which is able to model and analyze complex processes (Rozinat and Gunther, 2015) Even though it works with historical data, it does not mean that it is limited to offline analysis, as the results can be applied to running cases (van der Aalst et al, 2012). Some of the techniques are easier for analysis, and it is used in combination with ProM
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have