Tactical pattern recognition in soccer games by means of special self-organizing maps.

Increasing amounts of data are collected in sports due to technological progress. From a typical soccer game, for instance, the positions of the 22 players and the ball can be recorded 25 times per second, resulting in approximately 135.000 datasets. Without computational assistance it is almost impossible to extract relevant information from the complete data. This contribution introduces a hierarchical architecture of artificial neural networks to find tactical patterns in those positional data. The results from the classification using the hierarchical setup were compared to the results gained by an expert manually classifying the different categories. Short and long game initiations can be detected with relative high accuracy leading to the conclusion that the hierarchical architecture is capable of recognizing different tactical patterns and variations in these patterns. Remaining problems are discussed and ideas concerning further improvements of classification are indicated.