TOWARDS AN ADAPTIVE COST-OPTIMIZATION FRAMEWORK FOR SOFTWARE MAINTENANCE: INTEGRATING PREDICTIVE MODELING WITH ORGANIZATIONAL READINESS

Ahmed Masih Uddin Siddiqi; Manoj  Varshney

doi:10.29121/shodhkosh.v7.i9s.2026.7999

Authors

Ahmed Masih Uddin Siddiqi Department of Computer Engineering and Applications, Mangalayatan University, Aligarh, Uttar Pradesh, India
Manoj Varshney Department of Computer Engineering and Applications, Mangalayatan University, Aligarh, Uttar Pradesh, India

DOI:

https://doi.org/10.29121/shodhkosh.v7.i9s.2026.7999

Keywords:

Software Maintainance, Cost Optimization, Organizational Readiness, Adaptive Framework, Xgboost, Devops Integration, Resource Allocation, Predictive Maintenances

Abstract [English]

It imparts no less than 60 to 90 percent of total software lifetime costs on software maintenance but usage of predictive maintenance models in practice is infrequent. Past research has already defined two coordination findings: First, machine learning-based models of effort (such as Predictive Maintenance Effort Model (PMEM)) are capable of reducing resource misallocation by over 95 percent relative to the reactive approaches; and second, technical and organizational factors and obstacles machine learning based models have included inadequate data on defects, insufficient documentation, reliance on tacit knowledge, and resistance to Nevertheless, the predictive accuracy is not integrated with the organizational readiness as a requirement to deployment as a unified framework. The following paper presents a proposal of the Adaptive Cost-Optimization Framework (ACOF), a three-layer architecture, which includes a quantified Readiness Assessment Module, an adaptive Predictive Effort Engine that builds on the capabilities of PMEM and a continuous feedback loop, and a Governance and Monitoring Layer capable of being integrated with DevOps. The study of ACOF is assessed by simulating projects on a low, medium and high readiness level. Findings show that ACOF decreases even more the Sum of Squared Errors misallocation proxy than baseline PMEM and the greatest benefits are found in high-readiness settings. The framework offers an actionable pathway that these organizations and in particular the Small-to-Medium Enterprises (SMEs) can adopt to transform the reactive-based maintenance expenditure to be an informed cost governance.

References

Achouch, M., Dimitrova, M., Ziane, K., Sattarpanah Karganroudi, S., Dhouib, R., Ibrahim, H., & Adda, M. (2022). On Predictive Maintenance in Industry 4.0: Overview, Models, and Challenges. Applied Sciences, 12(16), 8081. https://doi.org/10.3390/app12168081 DOI: https://doi.org/10.3390/app12168081

Al Hadwer, A., Tavana, M., Gillis, D., & Rezania, D. (2021). A Systematic Review of Organizational Factors Impacting Cloud-based Technology Adoption Using Technology-Organization-Environment Framework. Internet of Things, 15, 100407. https://doi.org/10.1016/j.iot.2021.100407 DOI: https://doi.org/10.1016/j.iot.2021.100407

Almogahed, A., Mahdin, H., Omar, M., Zakaria, N. H., Mostafa, S. A., AlQahtani, S. A., Pathak, P., Shaharudin, S. M., & Hidayat, R. (2023). A Refactoring Classification Framework for Efficient Software Maintenance. IEEE Access, 11, 78904–78917. https://doi.org/10.1109/ACCESS.2023.3298678 DOI: https://doi.org/10.1109/ACCESS.2023.3298678

Alsolai, H., & Roper, M. (2022). The Impact of Ensemble Techniques on Software Maintenance Change Prediction: An Empirical Study. Applied Sciences, 12(10), 5234. https://doi.org/10.3390/app12105234 DOI: https://doi.org/10.3390/app12105234

Brown, S. A., Chen, L., & Miller, J. (2024). Comparative study of ensemble methods for predicting maintenance effort in software projects. Journal of Systems and Software, 205, 111818.

Chen, G., Wang, Y., & Zhang, H. (2024). Re-evaluating traditional cost estimation models in agile software maintenance. Information and Software Technology, 170, 107085.

Garcia, M., Lopez, A., & Ruiz, P. (2023). AI-driven decision support for resource allocation in software maintenance. Expert Systems with Applications, 220, 119745.

Greiner, D., & Cacereno, A. (2024). Enhancing the maintenance strategy and cost in systems with surrogate assisted multiobjective evolutionary algorithms. Developments in the Built Environment, 19, 100478. DOI: https://doi.org/10.1016/j.dibe.2024.100478

Islam, Z., Aftab, S., & Ahmad, M. (2023). Machine learning approaches for software maintenance cost estimation. Journal of King Saud University – Computer and Information Sciences, 35(2), 101416.

Johnson, R., & Lee, S. (2023). Drivers of maintenance cost in evolving software systems. Journal of Software: Evolution and Process, 35(9), e2545.

Miloudi, C., Cheikhi, L., & Abran, A. (2022). Systematic Review of Machine Learning-Based Open-Source Software Maintenance Effort Estimation. Recent Advances in Computer Science and Communications, 16(3). https://doi.org/10.2174/2666255816666220609110712 DOI: https://doi.org/10.2174/2666255816666220609110712

Qian, C., Liu, W., Liu, H., Chen, N., Dang, Y., Li, J., Yang, C., Chen, W., Su, Y., Cong, X., Xu, J., Li, D., Liu, Z., & Sun, M. (2024). ChatDev: Communicative Agents for Software Development. arXiv preprint. DOI: https://doi.org/10.18653/v1/2024.acl-long.810

Siddiqi, A. M. U., & Varshney, M. (2024a). Predictive Maintenance Effort Model (PMEM): Cost-Effective Approach in Software Maintenance. Mangalayatan University.

Siddiqi, A. M. U., & Varshney, M. (2024b). Implementation Challenges and Best Practices in Cost-Effective Software Maintenance. Mangalayatan University.

Singh, A., Raj, K., Kumar, T., Verma, S., & Roy, A. (2023). Deep Learning-Based Cost-Effective and Responsive Robot for Autism Treatment. Drones, 7(2), 81. https://doi.org/10.3390/drones7020081 DOI: https://doi.org/10.3390/drones7020081

Teoh, Y. K., Gill, S. S., & Parlikad, A. K. (2023). IoT and Fog-Computing-Based Predictive Maintenance Model for Effective Asset Management in Industry 4.0 Using Machine Learning. IEEE Internet of Things Journal, 10(3), 2087–2094. DOI: https://doi.org/10.1109/JIOT.2021.3050441

van Dinter, R., Tekinerdogan, B., & Catal, C. (2022). Predictive maintenance using digital twins: A systematic literature review. Information and Software Technology, 151, 107008. DOI: https://doi.org/10.1016/j.infsof.2022.107008

Wang, B., Liu, H., & Zhou, R. (2022). Cost drivers of software maintenance in modern development practices. Information and Software Technology, 142, 106721.

Zhou, Q., Chen, S., & Liu, Y. (2024). Proactive prediction of software maintenance effort using machine learning. Expert Systems with Applications, 238, 122241.