An Analytical Review on Feature Reduction for Big Data Analytics using Machine Learning

Abstract

There is an explosive growth of data due to advancements in computer methods. With ML techniques, working on a really massive quantity of data is a big problem. As a result, handling and computing on a very vast, varied, and diverse dataset seems a difficult undertaking. The purpose of this study is to provide a quick overview of several dimensionality reduction/feature selection techniques. A summary of the contributions of scholars to the development of feature selection methods for huge datasets is provided. This study is driven to create a hybrid, resilient, adjustable, as well as dynamical feature selection approach to classify huge datasets by examining current challenges.