A Survey On Static And Online Feature Selection Algorithms In Big Data For Classification Accuracy

Abstract

In current age of IT, handling massive data with higher dimension is a big challenge because of
the presence of superfluous features. The presence of the irrelevant features in voluminous amount in
data degrades the level of classification results and hence selecting features has a strong effect on the
success rate of any project. Classification Accuracy in machine learning applications is achieved by
feature reduction techniques so that the model generalizes well for new data. This paper focuses on the
study of feature selection techniques for various types of static and streaming feature selection models
with different measures and parameters.