Soccer Match Algorithm for Global Optimization: A Contender Metaheuristic

In the quest for enhancing global optimization techniques, this paper introduces the Soccer Match Algorithm (SMA), a novel metaheuristic inspired by soccer dynamics. SMA models the strategic elements of a soccer game including tactical roles, compositions, playing styles, and player interactions. Existing metaheuristic algorithms often struggle with the balance between reliability and computational efficiency. Furthermore, many algorithms lack the adaptive mechanisms necessary for dynamic parameter tuning which are based on ongoing performance feedback. The objective of this research is to create a soccer-inspired algorithm that integrates an unprecedented array of soccer concepts and characteristics, alongside an adaptive learning framework, to dynamically boost performance and efficiency. This approach is novel among soccer-inspired algorithms. SMA is designed using simple, soccer-related conceptual frameworks such as player roles and game tactics. It includes mechanisms for dynamic parameter adjustment and tactical shifts during a game. The algorithm’s effectiveness was assessed through a series of benchmark unconstrained optimization problems. The experimental analysis reveals that SMA achieves remarkable performance metrics, closely matching those of leading metaheuristics like Harris Hawks Optimization and other soccer-inspired methods such as the Tiki-Taka Algorithm. Notably, SMA demonstrates high scalability, reliability, and operational efficiency with minimal computational effort. The obtained results make SMA a promising approach for optimization problems.