Open AccessA Comparative Analysis of Filter-Based Feature Selection Methods for Software Fault Prediction
Author(s) -
Thị Minh Phương Hà,
Thi My Hanh Le,
Thanh Bình Nguyễn
Publication year - 2021
Publication title -
công trình nghiên cứu công nghệ thông tin truyền thông
Language(s) - English
Resource type - Journals
ISSN - 1859-3526
DOI - 10.32913/mic-ict-research-vn.v2021.n1.969
Subject(s) - feature selection , computer science , data mining , filter (signal processing) , ranking (information retrieval) , machine learning , software , feature (linguistics) , artificial intelligence , curse of dimensionality , selection (genetic algorithm) , fault (geology) , seismology , geology , linguistics , philosophy , computer vision , programming language
The rapid growth of data has become a huge challenge for software systems. The quality of fault predictionmodel depends on the quality of software dataset. High-dimensional data is the major problem that affects the performance of the fault prediction models. In order to deal with dimensionality problem, feature selection is proposed by various researchers. Feature selection method provides an effective solution by eliminating irrelevant and redundant features, reducing computation time and improving the accuracy of the machine learning model. In this study, we focus on research and synthesis of the Filter-based feature selection with several search methods and algorithms. In addition, five filter-based feature selection methods are analyzed using five different classifiers over datasets obtained from National Aeronautics and Space Administration (NASA) repository. The experimental results show that Chi-Square and Information Gain methods had the best influence on the results of predictive models over other filter ranking methods.