Pedro Passos, a researcher in sports analytics, has introduced a groundbreaking approach to real-time substitution decisions in elite soccer. His work, titled “AI-Assisted Game Management Decisions: A Fuzzy Logic Approach to Real-Time Substitutions,” presents a Decision Support System (DSS) that leverages Fuzzy Logic to provide prescriptive game management. This system stands out from traditional Machine Learning models by using an objective, rule-based inference engine rather than replicating historical biases.
The core of Passos’ innovation lies in the reformulation of the PlayerRank metric into a Cumulative Mean with Role Aware Normalization. This adjustment eliminates the playtime exposure bias found in cumulative sum models, enabling accurate intra-match comparisons. The DSS integrates this refined metric with physiological proxies, such as fatigue, and contextual variables, like disciplinary risk modulated by tactical role, to calculate a dynamic Substitution Priority (P_final).
Validation of the system was conducted through a case study of the 2018 FIFA World Cup match between Brazil and Belgium. The results were promising: the system not only aligned with expert consensus on executed substitutions, such as that of Gabriel Jesus, but also identified high-risk scenarios that human decision-makers overlooked. Notably, the model flagged the “Fagner Paradox,” a maximum priority defensive risk, minutes before a critical yellow card, and detected the “Lukaku Paradox,” where an isolated assist masked a severe drop in participation.
Passos’ research demonstrates that Fuzzy Logic offers a transparent, explainable, and superior alternative to black-box models for optimizing real-time tactical decisions. This approach could revolutionize game management in elite soccer, providing coaches with data-driven insights to make critical substitution decisions that could significantly impact the outcome of matches. The practical applications of this system extend beyond soccer, offering potential benefits for other sports that rely on real-time strategic decisions. Read the original research paper here.