This systematic review delves into the landscape of feature selection techniques integrated with metaheuristic algorithms, offering a comprehensive analysis of developments spanning the years 2019–2024. Feature selection is a pivotal process in machine learning, optimizing model performance by identifying and retaining pertinent features. The incorporation of metaheuristic algorithms enhances this process by providing efficient and effective optimization mechanisms. Through a meticulous examination of the literature, this review categorizes and evaluates diverse feature selection methods, including filter, wrapper, and embedded approaches. Additionally, the study investigates the application of prominent metaheuristic algorithms such as Butterfly Optimization Algorithm, Moth Flame Optimization, and Whale Optimization Algorithm in the context of feature selection. This review serves as a valuable resource for researchers, practitioners, and enthusiasts navigating the evolving landscape of feature selection methodologies and their integration with metaheuristic optimization strategies.