In table tennis, serves play a crucial role as they are the first and only shot during which players have full control of the game. In this paper, we explore serve techniques and tactics using a dataset of 9 games and a total of 510 serves collected semi-automatically for 5 players. We first provide a descriptive analysis and group the data into clusters to identify what we refer to as a serve repertoire, which are serve categories specific to players. We then identify which serve is used during the game and the tactic players employ during competitions. In particular, we provide a better understanding of the notion of variation, a concept often used in table tennis, and we show the differences in serves that are used in key moments of a game (e. g., during score domination, decisive points).
© Copyright 2025 Machine Learning and Data Mining for Sports Analytics. MLSA 2024. Communications in Computer and Information Science. Published by Springer. All rights reserved.