What Happened Next? Using Deep Learning to Value Defensive Actions in Football Event-Data

  title={What Happened Next? Using Deep Learning to Value Defensive Actions in Football Event-Data},
  author={Charbel Merhej and Ryan Beal and S. Ramchurn and Tim Matthews},
  journal={Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery \& Data Mining},
Objectively quantifying the value of player actions in football (soccer) is a challenging problem. To date, studies in football analytics have mainly focused on the attacking side of the game, while there has been less work on event-driven metrics for valuing defensive actions (e.g., tackles and interceptions). Therefore in this paper, we use deep learning techniques to define a novel metric that values such defensive actions by studying the threat of passages of play that preceded them. By… Expand


Decomposing the Immeasurable Sport: A deep learning expected possession value framework for soccer
What is the right way to think about analytics in soccer? Is the sport about measured events such as passes and goals, possession percentages and traveled distance, or even more abstract notions suchExpand
Actions Speak Louder than Goals: Valuing Player Actions in Soccer
A new language for describing individual player actions on the pitch and a framework for valuing any type of player action based on its impact on the game outcome while accounting for the context in which the action happened are introduced. Expand
"Quality vs Quantity": Improved Shot Prediction in Soccer using Strategic Features from Spatiotemporal Data
In this paper, we present a method which accurately estimates the likelihood of chances in soccer using strategic features from an entire season of player and ball tracking data taken from aExpand
An examination of expected goals and shot efficiency in soccer
The aim of this study was to examine goal scoring in European football leagues and specifically which factors are associated with predicting Expected Goals (xG). This concept helps us to evaluateExpand
Artificial intelligence for team sports: a survey
Assessing the work in how AI is used to predict match outcomes and to help sports teams improve their strategic and tactical decision making in team sports highlights not only a number of strengths but also weaknesses of the models and techniques that have been employed. Expand
A Markov Game model for valuing actions, locations, and team performance in ice hockey
Model validation shows that the total team action and state value both provide a strong indicator predictor of team success, as measured by the team’s average goal ratio. Expand
Beyond crowd judgments: Data-driven estimation of market value in association football
Association football is a popular sport, but it is also a big business. From a managerial perspective, the most important decisions that team managers make concern player transfers, so issues relatedExpand
Optimising Game Tactics for Football
Empirical evaluation of the approach on real-world datasets shows that by using optimised tactics from the Bayesian and stochastic games, the team chances of winning can be increased by up to 16.1\% and 3.4\% respectively. Expand
PROTECT: An Application of Computational Game Theory for the Security of the Ports of the United States
This paper presents PROTECT, a game-theoretic system deployed by the United States Coast Guard in the port of Boston for scheduling their patrols, and offers five key innovations, including a departure from the assumption of perfect adversary rationality and a quantal response model of the adversary's behavior. Expand
Leveraging Statistical Multi-Agent Online Planning with Emergent Value Function Approximation
This paper proposes Emergent Value function Approximation for Distributed Environments (EVADE), an approach to integrate global experience into multi-agent online planning in stochastic domains to consider global effects during local planning. Expand