Optimizing Feature Selection with Genetic Algorithms: A Review of Methods and Applications

TL;DR

This paper reviews the use of genetic algorithms for feature selection in machine learning, highlighting their effectiveness in improving model performance and reducing complexity across various applications.

Contribution

It provides a systematic review of GA-based feature selection methods, emphasizing hybrid approaches and their advancements in addressing key challenges.

Findings

Hybrid GA methods improve search efficiency

GA techniques enhance feature selection accuracy

Applications span multiple domains

Abstract

Analyzing large datasets to select optimal features is one of the most important research areas in machine learning and data mining. This feature selection procedure involves dimensionality reduction which is crucial in enhancing the performance of the model, making it less complex. Recently, several types of attribute selection methods have been proposed that use different approaches to obtain representative subsets of the attributes. However, population-based evolutionary algorithms like Genetic Algorithms (GAs) have been proposed to provide remedies for these drawbacks by avoiding local optima and improving the selection process itself. This manuscript presents a sweeping review on GA-based feature selection techniques in applications and their effectiveness across different domains. This review was conducted using the PRISMA methodology; hence, the systematic identification, screening, and analysis of relevant literature were performed. Thus, our results hint that the field's hybrid GA methodologies including, but not limited to, GA-Wrapper feature selector and HGA-neural networks, have substantially improved their potential through the resolution of problems such as exploration of unnecessary search space, accuracy performance problems, and complexity. The conclusions of this paper would result in discussing the potential that GAs bear in feature selection and future research directions for their enhancement in applicability and performance.