Analysing Soccer Games with Clustering and Conceptors

TL;DR

This paper introduces an unsupervised neural network-based method for analyzing soccer games by identifying and segmenting key situations and behaviors without relying on predefined concepts, using clustering and conceptors.

Contribution

It presents a novel approach combining recurrent neural networks, clustering, and conceptors to automatically identify and predict situations in soccer matches without prior domain knowledge.

Findings

Successfully segments soccer games into meaningful situations

Learns conceptors that improve future situation prediction

Demonstrates effectiveness in a simulated soccer environment

Abstract

We present a new approach for identifying situations and behaviours, which we call "moves", from soccer games in the 2D simulation league. Being able to identify key situations and behaviours are useful capabilities for analysing soccer matches, anticipating opponent behaviours to aid selection of appropriate tactics, and also as a prerequisite for automatic learning of behaviours and policies. To support a wide set of strategies, our goal is to identify situations from data, in an unsupervised way without making use of pre-defined soccer specific concepts such as "pass" or "dribble". The recurrent neural networks we use in our approach act as a high-dimensional projection of the recent history of a situation on the field. Similar situations, i.e., with similar histories, are found by clustering of network states. The same networks are also used to learn so-called conceptors, that are lower-dimensional manifolds that describe trajectories through a high-dimensional state space that enable situation-specific predictions from the same neural network. With the proposed approach, we can segment games into sequences of situations that are learnt in an unsupervised way, and learn conceptors that are useful for the prediction of the near future of the respective situation.