Feature Selection Techniques and its Importance in Machine Learning: A Survey

Abstract

Feature selection is well studied research topic in the field of artificial intelligence, machine learning and pattern recognition. Feature selection it removes the redundant, irrelevant and noisy features from the original features of datasets by choosing the relevant features having the smaller subdivision of dataset. By applying various techniques of feature selection to the datasets, results in lower computational costs, higher classifier accuracy, reduced dimensionality and predictable model. This article investigates, feature selection techniques found in various literatures.