Action rate models for predicting actions in soccer

Research output: Journal contributionsJournal articlesResearchpeer-review

Standard

Action rate models for predicting actions in soccer. / Dick, Uwe; Brefeld, Ulf.

In: AStA Advances in Statistical Analysis, Vol. 107, No. 1-2, 02.03.2022, p. 29-49.

Research output: Journal contributionsJournal articlesResearchpeer-review

Harvard

APA

Vancouver

Bibtex

@article{f7a1c0f051d44451b1779a36b92a033a,
title = "Action rate models for predicting actions in soccer",
abstract = "We present a data-driven approach to predict the next action in soccer. We focus on passing actions of the ball possessing player and aim to forecast the pass itself and when, in time, the pass will be played. At the same time, our model estimates the probability that the player loses possession of the ball before she can perform the action. Our approach consists of parameterized exponential rate models for all possible actions that are adapted to historic data with graph recurrent neural networks to account for inter-dependencies of the output space (i.e., the possible actions). We report on empirical results.",
keywords = "Informatics, Actions, Elite sports, Football, Game flow, GRNNs, Rate models, Soccer analytics, Actions, Elite sports, Football, GRNNs, Game flow, Rate models, Soccer analytics, Business informatics",
author = "Uwe Dick and Ulf Brefeld",
note = "Publisher Copyright: {\textcopyright} 2022, The Author(s).",
year = "2022",
month = mar,
day = "2",
doi = "10.1007/s10182-022-00435-x",
language = "English",
volume = "107",
pages = "29--49",
journal = "AStA Advances in Statistical Analysis",
issn = "1863-8171",
publisher = "German Statistical Society",
number = "1-2",

}

RIS

TY - JOUR

T1 - Action rate models for predicting actions in soccer

AU - Dick, Uwe

AU - Brefeld, Ulf

N1 - Publisher Copyright: © 2022, The Author(s).

PY - 2022/3/2

Y1 - 2022/3/2

N2 - We present a data-driven approach to predict the next action in soccer. We focus on passing actions of the ball possessing player and aim to forecast the pass itself and when, in time, the pass will be played. At the same time, our model estimates the probability that the player loses possession of the ball before she can perform the action. Our approach consists of parameterized exponential rate models for all possible actions that are adapted to historic data with graph recurrent neural networks to account for inter-dependencies of the output space (i.e., the possible actions). We report on empirical results.

AB - We present a data-driven approach to predict the next action in soccer. We focus on passing actions of the ball possessing player and aim to forecast the pass itself and when, in time, the pass will be played. At the same time, our model estimates the probability that the player loses possession of the ball before she can perform the action. Our approach consists of parameterized exponential rate models for all possible actions that are adapted to historic data with graph recurrent neural networks to account for inter-dependencies of the output space (i.e., the possible actions). We report on empirical results.

KW - Informatics

KW - Actions

KW - Elite sports

KW - Football

KW - Game flow

KW - GRNNs

KW - Rate models

KW - Soccer analytics

KW - Actions

KW - Elite sports

KW - Football

KW - GRNNs

KW - Game flow

KW - Rate models

KW - Soccer analytics

KW - Business informatics

UR - http://www.scopus.com/inward/record.url?scp=85125542114&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/c725041f-72b8-3ca5-9e45-35599a6500d0/

U2 - 10.1007/s10182-022-00435-x

DO - 10.1007/s10182-022-00435-x

M3 - Journal articles

AN - SCOPUS:85125542114

VL - 107

SP - 29

EP - 49

JO - AStA Advances in Statistical Analysis

JF - AStA Advances in Statistical Analysis

SN - 1863-8171

IS - 1-2

ER -