Journal ArticleParallel publicationPublished version DOI: 10.48548/pubdata-1507

Rating Player Actions in Soccer

Preview & Downloads

Chronological data

Date of first publication2021-07-15
Date of publication in PubData 2024-11-19

Language of the resource

English

Related external resources

Variant form of DOI: 10.3389/fspor.2021.682986
Dick, U., Tavakol, M., Brefeld, U. (2021). Rating Player Actions in Soccer. Frontiers in Sports and Active Living, 3, Article 682986.
Published in ISSN: 2624-9367
Frontiers in Sports and Active Living

Related PubData resources

Publisher

Other contributors

Abstract

We present a data-driven model that rates actions of the player in soccer with respect to their contribution to ball possession phases. This study approach consists of two interconnected parts: (i) a trajectory prediction model that is learned from real tracking data and predicts movements of players and (ii) a prediction model for the outcome of a ball possession phase. Interactions between players and a ball are captured by a graph recurrent neural network (GRNN) and we show empirically that the network reliably predicts both, player trajectories as well as outcomes of ball possession phases. We derive a set of aggregated performance indicators to compare players with respect to. to their contribution to the success of their team.

Keywords

Sports Analytics; Soccer; Graph Networks; Trajectory Prediction; Trajectory Data

Faculty / department

Notes

This publication was funded by the Open Access Publication Fund of Leuphana University Lüneburg.

More information

DDC

Creation Context

Research