The application of Evolutionary and Nature Inspired Algorithms in Data Science and Data Analytics

TL;DR

This paper reviews how evolutionary and nature-inspired algorithms have been applied in data science and analytics, focusing on optimization techniques for feature selection, hyper-parameter tuning, knowledge discovery, and clustering.

Contribution

It provides a comprehensive overview of recent applications of bio-inspired algorithms in various data science tasks, highlighting specific optimization methods used.

Findings

Evolutionary algorithms improve feature selection processes.

Nature-inspired algorithms enhance hyper-parameter tuning.

Applications lead to better clustering and knowledge discovery.

Abstract

In the past 30 years, scientists have searched nature, including animals and insects, and biology in order to discover, understand, and model solutions for solving large-scale science challenges. The study of bionics reveals that how the biological structures, functions found in nature have improved our modern technologies. In this study, we present our discovery of evolutionary and nature-inspired algorithms applications in Data Science and Data Analytics in three main topics of pre-processing, supervised algorithms, and unsupervised algorithms. Among all applications, in this study, we aim to investigate four optimization algorithms that have been performed using the evolutionary and nature-inspired algorithms within data science and analytics. Feature selection optimization in pre-processing section, Hyper-parameter tuning optimization, and knowledge discovery optimization in supervised algorithms, and clustering optimization in the unsupervised algorithms.