Modern movement tracking technologies enable acquisition of high-quality data about movements of the players and the ball in the course of a football match. However, there is a big difference between the raw data and the insights into team behaviors that analysts would like to gain. To enable such insights, it is necessary first to establish relationships between the concepts characterizing behaviors and what can be extracted from data. This task is challenging since the concepts are not strictly defined. We systematically explore all stages of data analysis process and identify situations when purely computational or purely visual approaches are not sufficient thus calling for visual analytics that enables synergy of human and computational processing. Thus, computationally-supported human involvement is needed for validating derived data (e.g. quantification of passes or conflicting situations), tuning parameters of computations (e.g. quantification of pressure forces or pass chances) and pattern detection methods (e.g. quantification of the clustering of situations), and interpretation of findings (e.g. explaining team tactics and suggesting how to improve it). The key components of the proposed approach are space transformation, visually-validated calculation of derived attributes, selection of classes of situations based on interactive queries from multiple perspectives, quantification of the interestingness, and clustering of configurations, followed by a visual assessment of aggregated data. We shall demonstrate examples of an application of visual analytics approaches to exemplary problems of football analytics, based on real data and our experience of cooperation with domain experts.

Keynote talks by Natalia and Gennady Andrienko.