Handling class imbalance problem in software maintainability prediction: an empirical investigation

被引:4
|
作者
Malhotra, Ruchika [1 ]
Lata, Kusum [1 ,2 ]
机构
[1] Delhi Technol Univ, Dept Comp Sci & Engn, Discipline Software Engn, Delhi 110042, India
[2] Delhi Technol Univ, Univ Sch Management & Entrepreneurship, East Delhi Campus, Delhi 110095, India
关键词
software maintenance; software maintainability; imbalanced learning; DEFECT PREDICTION; NEURAL-NETWORKS; CODE CLONES; CLASSIFICATION; FRAMEWORK; TRACKING; MACHINE; MODELS;
D O I
10.1007/s11704-021-0127-0
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
As the complexity of software systems is increasing; software maintenance is becoming a challenge for software practitioners. The prediction of classes that require high maintainability effort is of utmost necessity to develop cost-effective and high-quality software. In research of software engineering predictive modeling, various software maintainability prediction (SMP) models are evolved to forecast maintainability. To develop a maintainability prediction model, software practitioners may come across situations in which classes or modules requiring high maintainability effort are far less than those requiring low maintainability effort. This condition gives rise to a class imbalance problem (CIP). In this situation, the minority classes' prediction, i.e., the classes demanding high maintainability effort, is a challenge. Therefore, in this direction, this study investigates three techniques for handling the CIP on ten open-source software to predict software maintainability. This empirical investigation supports the use of resampling with replacement technique (RR) for treating CIP and develop useful models for SMP.
引用
收藏
页数:14
相关论文
共 50 条
  • [41] Class-specific extreme learning machine for handling binary class imbalance problem
    Raghuwanshi, Bhagat Singh
    Shukla, Sanyam
    NEURAL NETWORKS, 2018, 105 : 206 - 217
  • [42] Handling Class Imbalance and Class Overlap in Machine Learning Applications for Undeclared Work Prediction
    Alogogianni, Eleni
    Virvou, Maria
    ELECTRONICS, 2023, 12 (04)
  • [43] Handling Class Imbalance in Link Prediction Using Learning to Rank Techniques
    Li, Bopeng
    Chaudhuri, Sougata
    Tewari, Ambuj
    THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2016, : 4226 - 4227
  • [44] Prediction of copper contamination in soil across EU using spectroscopy and machine learning: Handling class imbalance problem
    Qi, Chongchong
    Zhou, Nana
    Hu, Tao
    Wu, Mengting
    Chen, Qiusong
    Wang, Han
    Zhang, Kejing
    Lin, Zhang
    SMART AGRICULTURAL TECHNOLOGY, 2025, 10
  • [45] The class-imbalance problem for high-dimensional class prediction
    Lusa, Lara
    Blagus, Rok
    2012 11TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2012), VOL 2, 2012, : 123 - 126
  • [46] Class Imbalance Data-Generation for Software Defect Prediction
    Li, Zheng
    Zhang, Xingyao
    Guo, Junxia
    Shang, Ying
    2019 26TH ASIA-PACIFIC SOFTWARE ENGINEERING CONFERENCE (APSEC), 2019, : 276 - 283
  • [47] Prediction of Defective Software Modules Using Class Imbalance Learning
    Tomar, Divya
    Agarwal, Sonali
    APPLIED COMPUTATIONAL INTELLIGENCE AND SOFT COMPUTING, 2016, 2016
  • [48] Tackling class overlap and imbalance problems in software defect prediction
    Lin Chen
    Bin Fang
    Zhaowei Shang
    Yuanyan Tang
    Software Quality Journal, 2018, 26 : 97 - 125
  • [49] COSTE: Complexity-based OverSampling TEchnique to alleviate the class imbalance problem in software defect prediction
    Feng, Shuo
    Keung, Jacky
    Yu, Xiao
    Xiao, Yan
    Bennin, Kwabena Ebo
    Kabir, Md Alamgir
    Zhang, Miao
    INFORMATION AND SOFTWARE TECHNOLOGY, 2021, 129
  • [50] Tackling class overlap and imbalance problems in software defect prediction
    Chen, Lin
    Fang, Bin
    Shang, Zhaowei
    Tang, Yuanyan
    SOFTWARE QUALITY JOURNAL, 2018, 26 (01) : 97 - 125