Deep soccer analytics: learning an action-value function for evaluating soccer players
- PDF / 1,702,325 Bytes
- 29 Pages / 439.37 x 666.142 pts Page_size
- 59 Downloads / 189 Views
Deep soccer analytics: learning an action-value function for evaluating soccer players Guiliang Liu1 · Yudong Luo1
· Oliver Schulte1 · Tarak Kharrat2
Received: 12 September 2019 / Accepted: 10 July 2020 © The Author(s), under exclusive licence to Springer Science+Business Media LLC, part of Springer Nature 2020
Abstract Given the large pitch, numerous players, limited player turnovers, and sparse scoring, soccer is arguably the most challenging to analyze of all the major team sports. In this work, we develop a new approach to evaluating all types of soccer actions from play-by-play event data. Our approach utilizes a Deep Reinforcement Learning (DRL) model to learn an action-value Q-function. To our knowledge, this is the first actionvalue function based on DRL methods for a comprehensive set of soccer actions. Our neural architecture fits continuous game context signals and sequential features within a play with two stacked LSTM towers, one for the home team and one for the away team separately. To validate the model performance, we illustrate both temporal and spatial projections of the learned Q-function, and conduct a calibration experiment to study the data fit under different game contexts. Our novel soccer Goal Impact Metric (GIM) applies values from the learned Q-function, to measure a player’s overall performance by the aggregate impact values of his actions over all the games in a season. To interpret the impact values, a mimic regression tree is built to find the game features that influence the values most. As an application of our GIM metric, we conduct a case study to rank players in the English Football League Championship. Empirical evaluation indicates GIM is a temporally stable metric, and its correlations with standard measures of soccer success are higher than that computed with other state-of-the-art soccer metrics.
Responsible editor: Ira Assent, Carlotta Domeniconi, Aristides Gionis, Eyke Hüllermeier. Electronic supplementary material The online version of this article (https://doi.org/10.1007/s10618020-00705-9) contains supplementary material, which is available to authorized users.
B
Yudong Luo [email protected]
1
School of Computing Science, Simon Fraser University, and Sportlogiq Predictive Analytics, Burnaby, BC, Canada
2
Management School, University of Liverpool, Liverpool, UK
123
G. Liu et al.
Keywords Deep reinforcement learning · Action-value Q-function · Goal impact metric · Fine-tuning · Player ranking
1 Introduction: valuing actions and players A major task of sports statistics is player evaluation, which provides insight into the performance of a player (Schumaker et al. 2010). Performance evaluation is important for team management and fan engagement. For instance, fantasy leagues allow fans to draft or build their favourite team, based on the skills and the performance of players. With the arrival of high-frequency tracking systems and object detection algorithms, ever more data on the movement of players in professional sports have become available. There is a
Data Loading...
