A Markov Framework for Learning and Reasoning About Strategies in Professional Soccer

Abstract

Strategy-optimization is a fundamental element of dynamic and complex team sports such as soccer, American football, and basketball. As the amount of data that is collected from matches in these sports has increased, so has the demand for data-driven decisionmaking support. If alternative strategies need to be balanced, a data-driven approach can uncover insights that are not available from qualitative analysis. This could tremendously aid teams in their match preparations. In this work, we propose a novel Markov modelbased framework for soccer that allows reasoning about the specific strategies teams use in order to gain insights into the efficiency of each strategy. The framework consists of two components: (1) a learning component, which entails modeling a team’s offensive behavior by learning a Markov decision process (MDP) from event data that is collected from the team’s matches, and (2) a reasoning component, which involves a novel application of probabilistic model checking to reason about the efficacy of the learned strategies of each team. In this paper, we provide an overview of this framework and illustrate it on several use cases using real-world event data from three leagues. Our results show that the framework can be used to reason about the shot decision-making of teams and to optimise the defensive strategies used when playing against a particular team. The general ideas presented in this framework can easily be extended to other sports.

Towards maximizing expected possession outcome in soccer

“…rather than directly discovering the optimal ones. Exploring the effect of changing such decisions is studied by Van Roy et al 2 and Fernandez et al 8 in football, and Sandholtz and Bornn 3 and Sandholtz and Luke 11 in basketball. A comprehensive method must consider a wide set of actions and all exact player- and ball locations rather than team formations.…”

“…Current analytics methods on soccer decision making are limited to measuring the potential outcome of alternative decisions, 2,3 and action valuation methods are focused either on short-term (e.g. pass success and turnover probabilities) 4,5 or long-term (e.g.…”

“…We directly derive the optimal policy for teams in terms of ball locations instead of evaluating the effect of alternative policies and counterfactual reasoning such as: what could have happened if another destination had been selected? The advantage of our proposed method compared to the state-of-the-art is that we can directly evaluate the performance of following the optimal policy rather than counterfactual reasoning and what-if analysis 2 (e.g. what could have happened if the team had increased long or short pass/shot frequency by x%?).…”

Tactical Intelligent Decision Modelling in Sports Competitions Based on Reinforcement Learning Algorithms

“…They can then prescribe personalized training programs tailored to each athlete's unique strengths, weaknesses, and injury history, thereby enhancing their overall performance and reducing the risk of injury [15]. The integration of tactical intelligent decision modeling and reinforcement learning in sports has the potential to revolutionize coaching strategies, player development, and overall team performance [16]. Coaches and sports scientists can leverage these data-driven insights to make informed decisions about training methodologies, game strategies, player selection, and ingame tactics [17].…”

A data-driven approach to assist offensive and defensive players in optimal decision making

“…However, the action valuation method leaves the coaches with the value of the performed actions, without any proper proposal of alternative actions, let alone the optimal one. To fill this gap, a few counterfactual reasoning methods, for example, Van Roy et al, 8 and Sandholtz and Bornn 9,10 have been proposed that inspect the outcome of alternative decisions without the requirement of actual deployment in a match. Particularly, they provide answers to the questions such as What would have happened if the team had modified the frequency of a particular action by x%?…”