Optimising Long-Term Outcomes using Real-World Fluent Objectives: An Application to Football
This work addresses decision-making challenges for football teams by providing a method to improve long-term performance, though it appears incremental as it builds on existing optimization techniques in a specific domain.
The paper tackles the problem of optimizing long-term tactical and strategic decision-making in football by modeling teams' evolving objectives across a season, resulting in an average increase of up to 35.6% in teams' mean expected finishing distribution in the league based on simulations of 760 matches.
In this paper, we present a novel approach for optimising long-term tactical and strategic decision-making in football (soccer) by encapsulating events in a league environment across a given time frame. We model the teams' objectives for a season and track how these evolve as games unfold to give a fluent objective that can aid in decision-making games. We develop Markov chain Monte Carlo and deep learning-based algorithms that make use of the fluent objectives in order to learn from prior games and other games in the environment and increase the teams' long-term performance. Simulations of our approach using real-world datasets from 760 matches shows that by using optimised tactics with our fluent objective and prior games, we can on average increase teams mean expected finishing distribution in the league by up to 35.6%.