In invasion team sports, strategy can be inferred through the analysis of recurrent tactical patterns performed during the game. In basketball, offensive actions are connected during a ball possession producing distinct sequences, with particular features that may directly affect the offense outcome. These sequences of actions can be assessed to characterize a team strategy and its efficiency. The present study aimed to develop a method to evaluate sequences of offensive actions in basketball. Reliability and objectivity of the criteria applied for defining the different sequences of actions indicated adequate consistency (Kappa test > 0.78). Results evidenced that the proposed method was able to discriminate teams based on the registered differences of their strategy features.
© Copyright 2016 Proceedings of the 2016 International Association of Computer Science in Sport (IACSS) Conference. Published by FEF/UNICAMP. All rights reserved.