Research on software defect prediction based on machine learning

doi:10.11835/j.issn.1000-582X.2025.02.002

Home > Archive>Volume 48, Issue 2, 2025 >10-21. DOI:10.11835/j.issn.1000-582X.2025.02.002

Research on software defect prediction based on machine learning
DOI:
                        10.11835/j.issn.1000-582X.2025.02.002
                    
CSTR:
                        
                    
Author:
                        YU Hao1YU Hao
GAC Aion New Energy Automobile Co., Ltd., Guangzhou 511400, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
ZHANG Ying2ZHANG Ying
Syncore Autotech Co., Ltd., Guangzhou 510335, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
LI Qian3LI Qian
The Fifth Research Institute of Electronics, Ministry of Industry and Information Technology, Guangzhou 510463, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
JIANG Libiao4,6JIANG Libiao
a School of Mechanical Engineering and Robotics;School of Mechanical & Automotive Engineering, South China University of Technology, Guangzhou 510641, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
SHANG Yunpeng5SHANG Yunpeng
b. Institute of Engineering Research, Guangzhou City University of Technology, Guangzhou 510800, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site

                    
Affiliation:1.GAC Aion New Energy Automobile Co., Ltd., Guangzhou 511400, P. R. China;2.Syncore Autotech Co., Ltd., Guangzhou 510335, P. R. China;3.The Fifth Research Institute of Electronics, Ministry of Industry and Information Technology, Guangzhou 510463, P. R. China;4.a School of Mechanical Engineering and Robotics;5.b. Institute of Engineering Research, Guangzhou City University of Technology, Guangzhou 510800, P. R. China;6.School of Mechanical & Automotive Engineering, South China University of Technology, Guangzhou 510641, P. R. China
Clc Number:
Fund Project:Supported by National Natural Science Foundation of China（61602345）.

Article

Figures

Metrics

Reference

Cited by

Materials

Comments

Abstract:

With the gradual penetration of machine learning technology into various fields, software testing in the software development process is very important. Software defect prediction faces class imbalance problem and accuracy issue. This paper proposes a supervised learning-based software prediction method for solving these two core problems. The method adopts sample balancing technique, combined with synthetic minority over-sampling technique(SMOTE) and edited nearest neighbor(ENN) algorithm, to test local weight learning(LWL), J48, C4.8, random forest, Bayes net(BN), multilayer feedforward neural network(MFNN), supported vector machine(SVM), and naive Bayes key(NB-K). These algorithms are applied to three different datasets (KK1, KK3 and PK2) in the NASA database and their effects are compared and analyzed in detail. The results show that the random forest model combining SMOTE and ENN exhibits high efficiency and avoiding overfitting in dealing with class imbalance problems, which provides an effective way to solve the problem in software defect prediction.

Key words:software defect prediction;machine learning;class imbalance;XGBoost;random forest

Get Citation

喻皓,张莹,李倩,姜立标,尚云鹏.基于机器学习的软件缺陷预测研究[J].重庆大学学报,2025,48(2):10~21

Copy

Article Metrics

Abstract:
PDF:
HTML:
Cited by:

History

Received:April 20,2024
Revised:
Adopted:
Online: March 04,2025
Published:

Home

Get Citation

Related Videos

Share

Article Metrics

History

Article QR Code