TY - GEN
T1 - Graph Neural Networks to Predict Sports Outcomes
AU - Xenopoulos, Peter
AU - Silva, Claudio
N1 - Funding Information:
This work was partially supported by NSF awards: CCF-1533564, CNS-1544753, CNS-1730396, CNS-1828576.
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Predicting outcomes in sports is important for teams, leagues, bettors, media, and fans. Given the growing amount of player tracking data, sports analytics models are increasingly utilizing spatially-derived features built upon player tracking data. However, player-specific information, such as location, cannot readily be included as features themselves, since common modeling techniques rely on vector input. Accordingly, spatially-derived features are often constructed in relation to anchor objects, such as the distance to a ball or goal, through global feature aggregations, or via role-assignment schemes, where players are designated a distinct role in the game. In doing so, we sacrifice inter-player and local relationships in favor of global ones. To address this issue, we introduce a sport-agnostic, graph-based representation of game states. We use our proposed graph representation as input to graph neural networks to predict sports outcomes. Our approach preserves permutation invariance and allows for flexible player interaction weights. We improve upon state of the art for prediction tasks in both American football and Counter-Strike, a popular esport, reducing test set loss by 9% and 20%, respectively. Furthermore, we show how our approach can be used to answer what if questions.
AB - Predicting outcomes in sports is important for teams, leagues, bettors, media, and fans. Given the growing amount of player tracking data, sports analytics models are increasingly utilizing spatially-derived features built upon player tracking data. However, player-specific information, such as location, cannot readily be included as features themselves, since common modeling techniques rely on vector input. Accordingly, spatially-derived features are often constructed in relation to anchor objects, such as the distance to a ball or goal, through global feature aggregations, or via role-assignment schemes, where players are designated a distinct role in the game. In doing so, we sacrifice inter-player and local relationships in favor of global ones. To address this issue, we introduce a sport-agnostic, graph-based representation of game states. We use our proposed graph representation as input to graph neural networks to predict sports outcomes. Our approach preserves permutation invariance and allows for flexible player interaction weights. We improve upon state of the art for prediction tasks in both American football and Counter-Strike, a popular esport, reducing test set loss by 9% and 20%, respectively. Furthermore, we show how our approach can be used to answer what if questions.
KW - esports
KW - graph neural networks
KW - sports analytics
UR - http://www.scopus.com/inward/record.url?scp=85125300599&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85125300599&partnerID=8YFLogxK
U2 - 10.1109/BigData52589.2021.9671833
DO - 10.1109/BigData52589.2021.9671833
M3 - Conference contribution
AN - SCOPUS:85125300599
T3 - Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021
SP - 1757
EP - 1763
BT - Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021
A2 - Chen, Yixin
A2 - Ludwig, Heiko
A2 - Tu, Yicheng
A2 - Fayyad, Usama
A2 - Zhu, Xingquan
A2 - Hu, Xiaohua Tony
A2 - Byna, Suren
A2 - Liu, Xiong
A2 - Zhang, Jianping
A2 - Pan, Shirui
A2 - Papalexakis, Vagelis
A2 - Wang, Jianwu
A2 - Cuzzocrea, Alfredo
A2 - Ordonez, Carlos
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE International Conference on Big Data, Big Data 2021
Y2 - 15 December 2021 through 18 December 2021
ER -