A Comprehensive Review of Hybrid and Ensemble Methods in Machine Learning Modeling

Abstract: Conventional machine learning (ML) algorithms are rapidly advancing with the introduction of novel learning techniques. These models are continuously improving through hybridization and ensemble approaches, enhancing their computational efficiency, functionality, robustness, and accuracy. In recent years, numerous hybrid and ensemble ML models have been proposed. However, a comprehensive survey of these models is still lacking. This paper aims to address this gap by presenting a state-of-the-art review of emerging ML models, highlighting their performance, applications, and categorization through a novel taxonomy.

Keywords: machine learning; deep learning; ensemble models