A Comparative Review of Software Defect Prediction using Machine Learning Technique
Main Article Content
Abstract
Software defect prediction is an important research area in software engineering that aims to identify defect-prone software modules before software deployment. The early detection of software defects helps improve software quality, reduce maintenance costs, and minimize testing efforts. Traditional software testing methods often require considerable time and resources, making machine learning techniques valuable for automated defect prediction. This study presents a comparative review of software defect prediction using various machine learning techniques, including Decision Tree, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Logistic Regression, Naïve Bayes, and ensemble learning approaches. The review examines the role of software metrics, feature selection, data preprocessing, and classification algorithms in predicting defective and non-defective software modules. Furthermore, it discusses the advantages and limitations of different machine learning techniques in terms of prediction accuracy, precision, recall, F1-score, and computational efficiency. Particular attention is given to class imbalance, feature redundancy, dataset variability, and model generalization, which significantly influence prediction performance. The comparative analysis aims to identify methodological trends, research challenges, and opportunities for developing more reliable and efficient software defect prediction systems. The findings of this review can support researchers and software developers in selecting suitable machine learning approaches for software quality assurance and improving defect detection during the software development lifecycle.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
References
Z. Zhou, Y. Zhu, Q. Yu and J. Li, "Software Defect Prediction Method Based on Multi-Feature Fusion," 2025 25th International Conference on Software Quality, Reliability and Security (QRS), Hangzhou, China, 2025, pp. 529-539.
Siddika, Ayesha, Momotaz Begum, Fahmid Al Farid, Jia Uddin, and Hezerul Abdul Karim. 2025. "Enhancing Software Defect Prediction Using Ensemble Techniques and Diverse Machine Learning Paradigms" Eng 6, no. 7: 161.
S. Setia, K. K. Ravulakollu, K. Verma, S. Garg, S. K. Mishra and B. Sharan, "Software Defect Prediction using Machine Learning," 2024 11th International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India, 2024.
Albattah, Waleed, and Musaad Alzahrani. 2024. "Software Defect Prediction Based on Machine Learning and Deep Learning Techniques: An Empirical Approach" AI 5, no. 4: 1743-1758.
Muhammad Azam, Muhammad Nouman and Ahsan Rehman Gill, “Comparative Analysis of Machine Learning techniques to Improve Software Defect Prediction”, KIET Journal of Computing & Information Sciences [KJCIS] Vol. 5, Issue 2, 2022.
Perera, A., Aleti, A., Turhan, B. & Boehme, M. An experimental assessment of using theoretical defect predictors to guide searchbased sofware testing. IEEE Trans. Sofw. Eng. Vol. 1, issue 1, 2022.
Kabir, M. A., Keung, J., Turhan, B. & Bennin, K. E. Inter-release defect prediction with feature selection using temporal chunkbased learning: An empirical study. Appl. Sof Comput. 113, 107870, 2021.
Maddipati, S.; Srinivas, M. Machine learning approach for classification from imbalanced software defect data using PCA and CSANFIS. Mater. Today Proc. 52, 471, 2021.
Alsghaier, H. & Akour, M. Sofware fault prediction using particle swarm algorithm with genetic algorithm and support vector machine classifer. Sofw. Pract. Exp. 50(4), 407–427, 2020.
Yu, X., Bennin, K. E., Liu, J., Keung, J. W., Yin, X., & Xu, Z. An empirical study of learning to rank techniques for efort-aware defect prediction. In SANER 2019 - Proceedings of the IEEE 26th International Conference on Sofware Analysis, Evolution, and Reengineering, pp. 298–309, 2019.
Bach, T., Andrzejak, A., Pannemans, R. & Lo, D. Te impact of coverage on bug density in a large industrial sofware project. ACM/ IEEE Int. Symp. Empirical Sofw. Eng. Meas. (ESEM), 307–313, 2017.
Mohammed, R., Rawashdeh, J., & Abdullah, M. Machine Learning with Oversampling and Undersampling Techniques: Overview Study and Experimental Results. In 11th International Conference on Information and Communication Systems (ICICS), pp. 243–248, 2020.
Aljamaan, H.; Alazba, A. Software defect prediction using tree-based ensembles. In Proceedings of the 16th ACM International Conference on Predictive Models and Data Analytics in Software Engineering, Virtual USA, 8–9 November, pp. 1–10, 2020.
Li, R.; Zhou, L.; Zhang, S.; Liu, H.; Huang, X.; Sun, Z. Software Defect Prediction Based on Ensemble Learning. In Proceedings of the 2nd International Conference on Data Science and Information Technology, Seoul, Republic of Korea, 19–21, pp. 1–6, 2019.
Alsaeedi, A.; Khan, M.Z. Software Defect Prediction Using Supervised Machine Learning and Ensemble Techniques: A Comparative Study J. Softw. Eng. Appl. 12, 85–100, 2019.
Tua, F.M.; Sunindyo, W.D. Software Defect Prediction Using Software Metrics with Naïve Bayes and Rule Mining Association Methods. In Proceedings of the 5th International Conference on Science and Technology (ICST), Yogyakarta, Indonesia, pp. 1–5, 2019.
Manjula, C.; Florence, L. A Deep neural network based hybrid approach for software defect prediction using software metrics. Clust. Comput., 22, 9847–9863, 2019.
Manjula, C.; Florence, L. Hybrid approach for software defect prediction using machine learning with optimization technique. Int. J. Comput. Inf. Eng., 12, 28–32, 2018.