A Comparative Analysis for Filter-Based Feature Selection Techniques with Tree-based Classification

Abstract

The selection of features is crucial as an essential pre-processing method, used in the area of research as Data Mining, Text mining, and Image Processing. Raw datasets for machine learning, comprise a combination of multidimensional attributes which have a huge amount of size. They are used for making predictions. If these datasets are used for classification, due to the majority of the presence of features that are inconsistent and redundant, it occupies more resources according to time and produces incorrect results and effects on the classification. With the intention of improving the efficiency and performance of the classification, these features have to be eliminated. A variety of feature subset selection methods had been presented to find and eliminate as many redundant and useless features as feasible. A comparative analysis for filter-based feature selection techniques with tree-based classification is done in this research work. Several feature selection techniques and classifiers are applied to different datasets using the Weka Tool. In this comparative analysis, we evaluated the performance of six different feature selection techniques and their effects on decision tree classifiers using 10-fold cross-validation on three datasets. After the analysis of the result, It has been found that the feature selection method ChiSquaredAttributeEval + Ranker search with Random Forest classifier beats other methods for effective and efficient evaluation and it is applicable to numerous real datasets in several application domains