HYB-PARSIMONY: A hybrid approach combining Particle Swarm Optimization and Genetic Algorithms to find parsimonious models in high-dimensional datasets

• Published in: Neurocomputing (Amsterdam) 2023-12, Vol.560, p.126840, Article 126840
• Main Authors: Divasón, Jose, Pernia-Espinoza, Alpha, Martinez-de-Pison, Francisco Javier
• Format: Article
• Language: English
• Subjects: Auto machine learning; GA-PARSIMONY; HYB-PARSIMONY; Parsimonious modeling; PSO-PARSIMONY
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2023.126840

The PSO-PARSIMONY methodology (a heuristic for finding accurate and low-complexity models with particle swarm optimization (PSO)) allows obtaining machine learning models with a good balance between accuracy and complexity. However, when the datasets are of high dimensionality, the methodology does not sufficiently reduce the complexity of the models. This paper presents a new hybrid methodology, called HYB-PARSIMONY, that combines PSO with genetic algorithm (GA) based methods. In the early stages of the optimization process, GA methods have a preponderance to accelerate the search for parsimony. Later, PSO becomes more relevant to improve accuracy. This new methodology obtains significant improvements in the search for more accurate and low-complexity models in high-dimensional datasets. •Hybrid method for finding parsimonious models with particle swarm optimization and genetic algorithms.•The new proposal was compared to PSO-PARSIMONY and GA-PARSIMONY.•The new methodology performed better in the search in high dimensional datasets.•In the early stages of the optimization GA methods have a preponderance to accelerate the search for parsimony.•PSO methods becomes more relevant in the last iterations to improve accuracy.