Identifying Team Playing Styles Across Phases of Play: a User-Specific Cluster Framework

EasyChair Preprint 14049

Abstract

Investigating team performance within smaller periods of matches allows for the analysis of phase-specific team playing styles. The cluster framework described in this paper assists in identifying phase-specific team playing styles within team invasion sports that are vital for guiding in-match decisions. The clustering framework is applied in the context of Australian football, with the goal of identifying an interpretable number of clusters that represent the inherent grouping of team playing styles during match phases. This paper develops a novel clustering approach, proposing a composite clustering assessment index for the selection of the optimal feature transformation technique, clustering algorithm and number of clusters. The proposed composite index allows the integration of subject matter expert knowledge, ensuring that the resulting clusters are chosen optimally in alignment with the goals of the analysis.

Keyphrases: Australian football, Clustering framework, Phase of play, playing style, team sport

@booklet{EasyChair:14049,
  author    = {Samuel Moffatt and Ritu Gupta and Suman Rakshit and Brad Keller},
  title     = {Identifying Team Playing Styles Across Phases of Play: a User-Specific Cluster Framework},
  howpublished = {EasyChair Preprint 14049},
  year      = {EasyChair, 2024}}