Cost-Sensitive Hybrid Ensemble Deep Model for Software Defect Prediction on NASA Datasets
DOI:
https://doi.org/10.70454/JRIST.020104Keywords:
Software Defect Prediction, Cost-Sensitive Learning, Hybrid Ensemble, NASA DatasetAbstract
Software defect prediction is a crucial task for improving software reliability and reducing maintenance cost in large-scale software systems. One of the major challenges in defect prediction is severe class imbalance, where defective modules are significantly fewer than non-defective ones. Traditional machine learning models often fail to prioritize defect detection, leading to biased performance. This paper proposes a cost-sensitive hybrid ensemble deep model for software defect prediction using NASA benchmark datasets. The proposed framework integrates cost-sensitive learning with ensemble deep classification to enhance minority defect detection while maintaining overall predictive stability. A comprehensive pre-processing pipeline and multi-metric evaluation strategy are employed, including accuracy, precision, recall, F1-score, and ROC-AUC. Experimental results across eight NASA datasets demonstrate improved defective module detection and strong generalization capability. The proposed model provides a scalable and practical framework for intelligent software quality assurance in industrial environments.
References
[1] Msbah Ali 2024 Misbah Ali et al.,“Software Defect Prediction Using an Intelligent Ensemble-Based Model,”IEEE Access, 2024.
[2] S. Lessmann et al.,“Benchmarking Classification Models for Software Defect Prediction,” IEEE Transactions on Software Engineering, 2008.
[3] He and E. Garcia,“Learning from Imbalanced Data,” IEEE Transactions on Knowledge and Data Engineering, 2009.
[4] Z. Zhou,“Ensemble Methods: Foundations and Algorithms,” CRC Press, 2012.
[5] T. Hall et al.,“A Systematic Review of Fault Prediction Studies,” IEEE Transactions on Software Engineering, 2009.
[6] Ali, T. Mazhar, Y. Arif, S. Al-Otaibi, Y. Y. Ghadi, T. Shahzad, M. A. Khan, and H. Hamam,
[7] “Software Defect Prediction Using an Intelligent Ensemble-Based Model,”IEEE Access, vol. 12, pp. 1–15, 2024.
[8] Z. Li, X. Jing, and X. Zhu,“Cost-Sensitive Software Defect Prediction Based on Ensemble Learning,”IEEE Transactions on Reliability, vol. 69, no. 4, pp. 1–12, 2020.
[9] S. Wang and X. Yao,“Using Class Imbalance Learning for Software Defect Prediction,” IEEE Transactions on Software Engineering, vol. 46, no. 4, pp. 1–14, 2020.
[10] Y. Ma, G. Luo, X. Zeng, and A. Chen,“Transfer Learning for Cross-Project Defect Prediction,” IEEE Access, vol. 9, pp. 1–11, 2021.
[11] Y. Zhou, H. Chen, and J. Lu,“Deep Learning-Based Software Defect Prediction: A Survey,” IEEE Trans¬actions on Neural Networks and Learning Systems, vol. 32, no. 5, pp. 1–18, 2021.
[12] S. J. Pan and Q. Yang,“A Survey on Transfer Learning,” IEEE Transactions on Knowledge and Data Engineering, vol. 33, no. 10, pp. 1–19, 2021.
[13] Z. Xu, J. Liu, and Y. Zhang “Hybrid Deep Learning Models for Software Defect Prediction,” IEEE Access, vol. 10, pp. 1–13, 2022.
[14] Chen, B. Fang, Z. Shang, and Y. Tang, “Negative Samples Reduction in Software Defect Prediction,” IEEE Trans-actions on Software Engineering, vol. 48, no. 3, pp. 1–16, 2022.
[15] X. Yang and D. Lo, “Deep Learning for Just-In-Time Defect Prediction,” IEEE Software, vol. 39, no. 2, pp. 1–8, 2022.
[16] Liu, J. Zhou, and Y. Tian,“Ensemble Deep Learning for Imbalanced Software Defect Prediction,” IEEE Access, vol. 11, pp. 1–14, 2023.
[17] A. Khan and S. Hussain, “Cost-Sensitive Neural Networks for Software Quality Prediction,” IEEE Transactions on Reliability, vol. 72, no. 2, pp. 1–12, 2023.
A. Shukla and R. K. Singh, “Hybrid Machine Learning Models for Software Fault Prediction,” IEEE Access, vol. 11, pp. 1–10, 2023.
[18] Y. Zhao, L. Zhang, and X. Sun, “Attention-Based Deep Models for Software Defect Prediction,” IEEE Trans¬actions on Software Engineering, 2024.
[19] Patel and K. Shah, “A Comparative Study of Ensemble Techniques for Defect Prediction,” IEEE Access, vol. 12, pp. 1–9, 2024.
[20] R. Singh and P. Verma, “Cost-Aware Hybrid Deep Ensemble Model for Software Defect Prediction,” IEEE Access, 2025.
[21] S. Lessmann, B. Baesens, C. Mues, and S. Pietsch, “Benchmarking Classification Models for Software Defect Prediction,” IEEE Transactions on Software Engineering, vol. 34, no. 4, pp. 485–496, 2008.
[22] T. Hall, S. Beecham, D. Bowes, D. Gray, and S. Counsell, “A Systematic Literature Review on Fault Prediction Performance,” IEEE Transactions on Software Engineering, vol. 38, no. 6, pp. 1276–1304, 2012.
[23] Song, Y. Guo, and M. Shepperd, “A Comprehensive Investigation of the Role of Imbalanced Learning for Software Defect Prediction,” IEEE Transactions on Software Engineering, vol. 39, no. 6, pp. 1–15, 2011.
[24] Nam and S. Kim, “Heterogeneous Defect Prediction,” IEEE Transactions on Software Engi¬neering, vol. 41, no. 6, pp. 1–17, 2013.
[25] Y. Jiang, J. Lin, B. Cukic, and T. Menzies, “Variance Analysis in Software Fault Prediction Models,” IEEE Transactions on Software Engineering, vol. 36, no. 5, pp. 1–14, 2018.
[26] Z. Chen, T. Menzies, D. Port, and J. Hihn, “Simple Cross-Project Defect Prediction,” IEEE Software, vol. 36, no. 4, pp. 1–7, 2019.
[27] S. Wang, T. Liu, and L. Tan, “Automatically Learning Semantic Features for Defect Prediction,” IEEE Transactions on Software Engineering, vol. 45, no. 4, pp. 1–16, 2019.
[28] Y. Zhou, H. Chen, and J. Lu, “Deep Learning-Based Software Defect Prediction: A Survey,” IEEE Trans¬actions on Neural Networks and Learning Systems, vol. 31, no. 5, pp. 1–18, 2020.
[29] Z. Li, X. Jing, and X. Zhu, “Cost-Sensitive Software Defect Prediction Based on Ensemble Learning,” IEEE Transactions on Reliability, vol. 69, no. 4, pp. 1–12, 2020.
[30] Y. Ma, G. Luo, X. Zeng, and A. Chen, “Transfer Learning for Cross-Project Defect Prediction,” IEEE Access, vol. 9, pp. 1–11, 2021.
[31] Z. Xu, S. Zhang, and Y. Yang, “Deep Neural Networks for Software Defect Prediction,” Neural Computing and Applications, Springer, vol. 33, pp. 1–14, 2021.
[32] S. J. Pan and Q. Yang, “A Survey on Transfer Learning,” IEEE Transactions on Knowledge and Data Engineering, vol. 33, no. 10, pp. 1–19, 2021.
[33] X. Yang and D. Lo, “Deep Learning for Just-In-Time Defect Prediction,” IEEE Software, vol. 39, no. 2, pp. 1–8, 2022.
[34] Chen, B. Fang, Z. Shang, and Y. Tang,“Negative Samples Reduction in Software Defect Prediction,” IEEE Trans¬actions on Software Engineering, vol. 48, no. 3, pp. 1–16, 2022.
[35] Liu, J. Zhou, and Y. Tian, “Ensemble Deep Learning for Imbalanced Software Defect Prediction,”IEEE Access, vol. 11, pp. 1–14, 2023.
[36] A. Khan and S. Hussain,“Cost-Sensitive Neural Networks for Software Quality Prediction,” IEEE Transactions on Reliability, vol. 72, no. 2, pp. 1–12, 2023.
[37] A. Shukla and R. K. Singh,“Hybrid Machine Learning Models for Software Fault Prediction,” IEEE Access, vol. 11, pp. 1–10, 2023.
[38] Y. Zhao, L. Zhang, and X. Sun,“Attention-Based Deep Models for Software Defect Prediction,” IEEE Trans¬actions on Software Engineering, 2024.
[39] Singh and P. Verma,“Cost-Aware Hybrid Deep Ensemble Model for Software Defect Prediction,”IEEE Access, 2025.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Aditi gaur (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
This is an Open Access article distributed under the term's of the Creative Common Attribution 4.0 International License permitting all use, distribution, and reproduction in any medium, provided the work is properly cited.
