Learning to Rate Player Positioning in Soccer
Research output: Journal contributions › Journal articles › Research › peer-review
Standard
In: Big Data, Vol. 7, No. 1, 01.03.2019, p. 71-82.
Research output: Journal contributions › Journal articles › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Learning to Rate Player Positioning in Soccer
AU - Dick, Uwe
AU - Brefeld, Ulf
N1 - Publisher Copyright: Copyright 2019, Mary Ann Liebert, Inc., publishers
PY - 2019/3/1
Y1 - 2019/3/1
N2 - We investigate how to learn functions that rate game situations on a soccer pitch according to their potential to lead to successful attacks. We follow a purely data-driven approach using techniques from deep reinforcement learning to valuate multiplayer positionings based on positional data. Empirically, the predicted scores highly correlate with dangerousness of actual situations and show that rating of player positioning without expert knowledge is possible.
AB - We investigate how to learn functions that rate game situations on a soccer pitch according to their potential to lead to successful attacks. We follow a purely data-driven approach using techniques from deep reinforcement learning to valuate multiplayer positionings based on positional data. Empirically, the predicted scores highly correlate with dangerousness of actual situations and show that rating of player positioning without expert knowledge is possible.
KW - Informatics
KW - deep learning
KW - reinforcement learning
KW - scoring function
KW - spatiotemportal data
KW - Business informatics
UR - http://www.scopus.com/inward/record.url?scp=85063285321&partnerID=8YFLogxK
U2 - 10.1089/big.2018.0054
DO - 10.1089/big.2018.0054
M3 - Journal articles
C2 - 30672712
VL - 7
SP - 71
EP - 82
JO - Big Data
JF - Big Data
SN - 2167-6461
IS - 1
ER -