Software defect prediction proactively highlights critically vulnerable elements for a software system. Recent attempts in this domain have tried various machine learning techniques to automate and improve software defect prediction. It has been observed that recent research focusses on specific types of software and hence the solution is not suitable for all kind of software products.
JINAL GUPTA, DR. ANSHU KHURANA, NITISH UPPAL
Department of Artificial Intelligence and Data Science, Maharaja Agrasen Institute of Technology, Rohini, Delhi
Corresponding Author. E-mail:
Abstract: Software defect prediction proactively highlights critically vulnerable elements for a software system. Recent attempts in this domain have tried various machine learning techniques to automate and improve software defect prediction. It has been observed that recent research focusses on specific types of software and hence the solution is not suitable for all kind of software products. This paper proposes a generic approach based on Logistic Regression, Decision Trees, Random Forests, Naïve Bayes, Support Vector Machine for software defect prediction. Proposed approach is applicable on all type of software products and the results shows defect occurrence are not directly correlated with the quantity of modifications.
Keywords: Defect Prediction, Machine Learning Techniques, Software defect prediction Metrices, Ensemble Technique, Attribute correlation
REFERENCES
[1] Malhotra, R., & Khurana, A. (2017). Analysis of evolutionary algorithms to improve software defect prediction. 2017 6th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO).
[2] Ruchika Malhotra, “A systematic review of machine learning techniques for software fault prediction,” Appl. Soft Computing, vol. 27, pp. 504-518, 2015.
[3] Matloob, F., Ghazal, T. M., Taleb, N., Aftab, S., Ahmad, M., Khan, M. A., … Soomro, T. R. (2021). Software Defect Prediction Using Ensemble Learning: A Systematic Literature Review. IEEE Access, 9, 98754–98771.
[4] Song, Q., Guo, Y., & Shepperd, M. (2018). A Comprehensive Investigation of the Role of Imbalanced Learning for Software Defect Prediction. IEEE Transactions on Software Engineering, 1–1.
[5] A. B. Binkley and S. R. Schach, "Validation of the coupling dependency metric as a predictor of run-time failures and maintenance measures," Proceedings of the 20th International Conference on Software Engineering, Kyoto, Japan, 1998, pp. 452-455, doi: 10.1109/ICSE.1998.671604.
[6] S. R. Chidamber, D. P. Darcy and C. F. Kemerer, "Managerial use of metrics for object-oriented software: an exploratory analysis," in IEEE Transactions on Software Engineering, vol. 24, no. 8, pp. 629-639, Aug. 1998, doi: 10.1109/32.707698.
[7] S. R. Chidamber and C. F. Kemerer, "A metrics suite for object-oriented design," in IEEE Transactions on Software Engineering, vol. 20, no. 6, pp. 476-493, June 1994, doi: 10.1109/32.295895.
[8] Thota, M.K., Shajin, F.H., Rajesh, P. 2020. Survey on software defect prediction techniques. International Journal of Applied Science and Engineering, 17, 331–344.
[9] Rathore, Santosh S., and Sandeep Kumar. "An empirical study of ensemble techniques for software fault prediction." Applied Intelligence 51 (2021): 3615-3644.
[10] Goyal, Somya. "Handling class-imbalance with KNN (neighborhood) under-sampling for software defect prediction." Artificial Intelligence Review 55.3 (2022): 2023-2064.
