Recent advances in genetic algorithm-based feature selection: A comprehensive survey

Feature selection (FS) is a critical preprocessing step in machine learning, particularly when working with high-dimensional datasets that contain redundant or irrelevant information. Genetic Algorithms (GAs) have emerged as a powerful and flexible approach to FS due to their global search capabilities and adaptability. This survey reviews recent advances in GA-based FS, focusing on variations introduced over the past five years that improve selection efficiency, convergence behavior, and solution interpretability. We categorize these developments into population-level, selection and crossover-based, and mutation-based strategies, highlighting how each contributes to improved performance across diverse application domains, including network security, bioinformatics, industrial control systems, and medical diagnostics. Additionally, we outline current limitations in theoretical grounding and generalizability and propose future research directions aimed at integrating GA-based FS into Automated Machine Learning (AutoML) frameworks and explainable AI systems. The goal of this survey is to provide a comprehensive and critical overview of the evolving role of GAs in FS, serving as a foundation for both researchers and practitioners in the field.