Self-evolving Software Reliability Intelligence: A Continual Learning and Uncertainty-aware Framework for Cross-project Defect Prediction, Adaptive Risk Governance, and Autonomous Quality Assurance
DOI:
https://doi.org/10.63282/3050-9246.IJETCSIT-V5I1P123Keywords:
Software Defect Prediction, Cross-Project Defect Prediction, Continual Learning, Concept Drift, Uncertainty Estimation, Software Reliability, Decision Intelligence, Quality Assurance, Transfer LearningAbstract
Software defect prediction is commonly formulated as a stationary supervised-learning problem, although production software evolves through releases, architectural changes, dependency updates, shifting development practices, and heterogeneous project contexts. These changes can invalidate a model after deployment and can make point predictions appear more certain than the available evidence warrants. This paper proposes Self-Evolving Software Reliability Intelligence (SRI), a framework that unifies cross-project defect prediction, continual adaptation, predictive uncertainty, drift-aware model governance, and quality-assurance decision policies. SRI separates representation transfer from temporal adaptation and places an uncertainty-aware decision layer between prediction and engineering action. The framework maintains a bounded replay memory, monitors distributional and performance drift, calibrates predictive confidence, and selects among model reuse, incremental update, and controlled retraining. A risk-governance policy combines defect probability, uncertainty, software criticality, and inspection cost to prioritize testing without treating machine-learning output as an autonomous release authority. Because no original experimental measurements were supplied for this manuscript, the paper deliberately reports no fabricated accuracy, AUC, cost reduction, or statistical significance. Instead, it defines a reproducible evaluation protocol, hypotheses, ablations, metrics, and acceptance criteria that can be executed on public multi-project, multi-version defect datasets. The resulting contribution is a technically specified research framework and empirical design for studying whether adaptive, uncertainty-aware reliability intelligence can remain useful under cross-project distribution shift and software evolution.
References
[1] J. Chen, K. Hu, Y. Yang, Y. Liu, and Q. Xuan, “Collective transfer learning for defect prediction,” Neurocomputing, vol. 416, pp. 103–116, 2020, doi: 10.1016/j.neucom.2018.12.091.
[2] “A three-stage transfer learning framework for multi-source cross-project software defect prediction,” Information and Software Technology, vol. 150, Art. no. 106985, 2022, doi: 10.1016/j.infsof.2022.106985.
[3] Y. Zhu, Y. Zhao, Q. Yu, and X. Chen, “Cross-project defect prediction method based on feature distribution alignment and neighborhood instance selection,” Journal of Internet Technology, vol. 23, no. 4, 2022.
[4] “Cross-project defect prediction based on two-phase feature importance amplification,” Computational Intelligence and Neuroscience, 2022, Art. no. 2320447, doi: 10.1155/2022/2320447.
[5] “Towards building a pragmatic cross-project defect prediction model combining non-effort based and effort-based performance measures for a balanced evaluation,” Information and Software Technology, vol. 150, Art. no. 106980, 2022, doi: 10.1016/j.infsof.2022.106980.
[6] “How far does the predictive decision impact the software project? The cost, service time, and failure analysis from a cross-project defect prediction model,” Journal of Systems and Software, vol. 195, Art. no. 111522, 2023, doi: 10.1016/j.jss.2022.111522.
[7] M. A. Kabir, A. U. Rehman, M. M. M. Islam, N. Ali, and M. L. Baptista, “Cross-version software defect prediction considering concept drift and chronological splitting,” Symmetry, vol. 15, no. 10, Art. no. 1934, 2023, doi: 10.3390/sym15101934.
[8] “A paired learner-based approach for concept drift detection and adaptation in software defect prediction,” Applied Sciences, vol. 11, no. 14, Art. no. 6663, 2021, doi: 10.3390/app11146663.
[9] Gunda, S. K., Yettapu, S. D. R., Bodakunti, S., & Bikki, S. B. (2023). Decision Intelligence Methodology for AI-Driven Agile Software Lifecycle Governance and Architecture-Centered Project Management. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 4(1), 102-108. https://doi.org/10.63282/3050-9262.IJAIDSML-V4I1P112
[10] Sivva, S. D., Thalakanti, R. R., Bandari, S. S. G., & Yettapu, S. D. R. (2023). AI-Driven Decision Intelligence for Agile Software Lifecycle Governance: An Architecture-Centered Framework Integrating Machine Learning Defect Prediction and Automated Testing. International Journal of Emerging Trends in Computer Science and Information Technology, 4(4), 167-172. https://doi.org/10.63282/3050-9246.IJETCSIT-V4I4P118
[11] Gunda, S. K. G. (2023). The Future of Software Development and the Expanding Role of ML Models. International Journal of Emerging Research in Engineering and Technology, 4(2), 126-129. https://doi.org/10.63282/3050-922X.IJERET-V4I2P113
[12] Y. Gal and Z. Ghahramani, “Dropout as a Bayesian approximation: Representing model uncertainty in deep learning,” in Proc. 33rd Int. Conf. Machine Learning (ICML), 2016, pp. 1050–1059.
[13] B. Lakshminarayanan, A. Pritzel, and C. Blundell, “Simple and scalable predictive uncertainty estimation using deep ensembles,” in Advances in Neural Information Processing Systems, vol. 30, 2017.
[14] C. Guo, G. Pleiss, Y. Sun, and K. Q. Weinberger, “On calibration of modern neural networks,” in Proc. 34th Int. Conf. Machine Learning (ICML), 2017, pp. 1321–1330.
[15] S. Pal and A. Sillitti, “Cross-project defect prediction: A literature review,” IEEE Access, vol. 10, pp. 118697–118717, 2022, doi: 10.1109/ACCESS.2022.3221184.
[16] Y. Zhao, Y. Zhu, Q. Yu, and X. Chen, “Cross-project defect prediction considering multiple data distribution simultaneously,” Symmetry, vol. 14, no. 2, Art. no. 401, 2022, doi: 10.3390/sym14020401.
[17] “MSCPDPLab: A MATLAB toolbox for transfer learning based multi-source cross-project defect prediction,” SoftwareX, vol. 21, Art. no. 101286, 2023, doi: 10.1016/j.softx.2022.101286.
[18] Y. Khatri and S. K. Singh, “An effective software cross-project fault prediction model for quality improvement,” Science of Computer Programming, vol. 226, Art. no. 102918, Mar. 2023.
[19] J. Nam, S. J. Pan, and S. Kim, “Transfer defect learning,” in Proc. 35th Int. Conf. Software Engineering (ICSE), 2013, pp. 382–391.
[20] T. Menzies, J. Greenwald, and A. Frank, “Data mining static code attributes to learn defect predictors,” IEEE Transactions on Software Engineering, vol. 33, no. 1, pp. 2–13, Jan. 2007.
[21] T. Hall, S. Beecham, D. Bowes, D. Gray, and S. Counsell, “A systematic literature review on fault prediction performance in software engineering,” IEEE Transactions on Software Engineering, vol. 38, no. 6, pp. 1276–1304, Nov.–Dec. 2012.
[22] D. Sculley et al., “Hidden technical debt in machine learning systems,” in Advances in Neural Information Processing Systems, 2015, pp. 2503–2511.
