Rating Player Actions in Soccer

Uwe Dick; Maryam Tavakol; Ulf Brefeld

doi:10.3389/fspor.2021.682986

Rating Player Actions in Soccer

Uwe Dick
, Maryam Tavakol
, Ulf Brefeld^*

^*Korrespondierende/r Autor/-in für diese Arbeit

Professur für Wirtschaftsinformatik, insbesondere Machine Learning

Technische Universität Eindhoven

Publikation: Beiträge in Zeitschriften › Zeitschriftenaufsätze › Forschung › Begutachtung

10 Zitate (Scopus)

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.

Originalsprache	Englisch
Aufsatznummer	682986
Zeitschrift	Frontiers in Sports and Active Living
Jahrgang	3
Seitenumfang	14
ISSN	2642-9367
DOIs	https://doi.org/10.3389/fspor.2021.682986
Publikationsstatus	Erschienen - 15.07.2021

Bibliographische Notiz

Diese Publikation wurde gefördert durch den Open-Access-Publikationsfonds der Leuphana Universität Lüneburg.

UN SDGs

Dieser Output leistet einen Beitrag zu folgendem(n) Ziel(en) für nachhaltige Entwicklung

SDG 3 – Gute Gesundheit und Wohlergehen

Fachgebiete und Schlagwörter

Informatik
Wirtschaftsinformatik

ASJC Scopus Sachgebiete

Physiologie
Tourismus-, Freizeit- und Gastronomiemanagement
Orthopädie und Sportmedizin
Anthropologie
Öffentliche Gesundheit, Umwelt- und Arbeitsmedizin
Physiotherapie, Sporttherapie und Rehabilitation

Zugriff auf Dokument

10.3389/fspor.2021.682986Lizenz: CC BY

DownloadEndgültige, publizierte Fassung, 2,33 MBLizenz: CC BY

Rating Player Actions in Soccer
Dick, U. (Urheber*in), Tavakol, M. (Urheber*in) & Brefeld, U. (Urheber*in), Medien- und Informationszentrum, Leuphana Universität Lüneburg, 19.11.2024
DOI: 10.48548/pubdata-1507
Datensatz

Dieses zitieren

@article{5e7866ce44cf4d4caf5bbe6296bef8d2,

title = "Rating Player Actions in Soccer",

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 = "graph networks, soccer, sports analytics, trajectory data, trajectory prediction, Informatics, Business informatics",

author = "Uwe Dick and Maryam Tavakol and Ulf Brefeld",

note = "This publication was funded by the Open Access Publication Fund of Leuphana University L{\"u}neburg.",

year = "2021",

month = jul,

day = "15",

doi = "10.3389/fspor.2021.682986",

language = "English",

volume = "3",

journal = "Frontiers in Sports and Active Living",

issn = "2642-9367",

publisher = "Frontiers Media",

}

TY - JOUR

T1 - Rating Player Actions in Soccer

AU - Dick, Uwe

AU - Tavakol, Maryam

AU - Brefeld, Ulf

N1 - This publication was funded by the Open Access Publication Fund of Leuphana University Lüneburg.

PY - 2021/7/15

Y1 - 2021/7/15

N2 - 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.

AB - 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.

KW - graph networks

KW - soccer

KW - sports analytics

KW - trajectory data

KW - trajectory prediction

KW - Informatics

KW - Business informatics

UR - https://www.scopus.com/pages/publications/85124574199

U2 - 10.3389/fspor.2021.682986

DO - 10.3389/fspor.2021.682986

M3 - Journal articles

C2 - 34337404

AN - SCOPUS:85124574199

SN - 2642-9367

VL - 3

JO - Frontiers in Sports and Active Living

JF - Frontiers in Sports and Active Living

M1 - 682986

ER -

Rating Player Actions in Soccer

Abstract

Bibliographische Notiz

UN SDGs

Fachgebiete und Schlagwörter

ASJC Scopus Sachgebiete

Zugriff auf Dokument

Fingerprint

Forschungsdatensätze

Rating Player Actions in Soccer

Dieses zitieren