An integrated approach to forecasting software system quality using bayesian correction, multi-criteria optimization, and meta-learning

Anton Shantyr, Olha Zinchenko, Kamila Storchak, Viktor Vyshnivskyi, Olga Morozova

Abstract


The aim of this study is to improve modern methods for forecasting the quantitative characteristics of software system quality to enhance reliability, efficiency, and adaptability in dynamic IT environments. To achieve this, an integrated forecasting approach was developed that combines adaptive Bayesian noise correction, probabilistic ensembles with weighted risk adjustment, hybrid multi-criteria optimization, graph models of metric interdependencies, and meta-learning for forecast adaptation. The scientific novelty lies in the proposed ensemble integration and adaptive mechanisms that increase forecasting robustness while accounting for uncertainty and metric dependencies. The methods were validated on the GitLab CE system. The experimental results confirmed measurable improvements: forecasting error was reduced from 18.7% to 4.2%, execution time decreased by 36.8%, CPU and memory consumption dropped by up to 20%, and system reliability indicators (downtime, fault tolerance) improved by more than 60%. These metrics confirm that the proposed approach strengthens reliability, efficiency, and adaptability of software quality forecasting compared to traditional methods.

Keywords


software quality prediction; probabilistic ensembles; Bayesian correction; meta-learning; multi-criteria optimization

Full Text:

PDF

References


Almetwaly, A. A. I., & Fadhel, I. E. I. Integrate between information systems engineering and software engineering theories for successful quality engineering measurement of software: Valid instrument pre-results. Computer Software and Media Applications, 2024, vol. 6, iss. 1, article no. 3382. DOI: 10.24294/csma.v6i1.3382.

Côté, P.-O., Nikanjam, A., Bouchoucha, R., Basta, I., Abidi, M., & Khomh, F. Quality issues in machine learning software systems. Empirical Software Engineering, 2024, vol. 29, article no. 149. DOI: 10.1007/s10664-024-10536-7.

Pfeiffer, R.-H., & Aaen, J. Tools for monitoring software quality in information systems development and maintenance: Five key challenges and a design proposal. International Journal of Information Systems and Project Management, 2024, vol. 12, iss. 1, pp. 19-40. DOI: 10.12821/ijispm120102.

De Angelis, G., Do, H., & Nguyen, B. N. Introduction to the special issue: “software quality for modern systems”. Journal of Software: Evolution and Process, 2024, vol. 36, iss. 8, article no. e2663. DOI: 10.1002/smr.2663.

Ali, A. R., & Saleem, N. N. Classification of software systems attributes based on quality factors using linguistic knowledge and machine learning: A review. Journal of Education and Science, 2022, vol. 31, iss. 3, pp. 66–90. Available at: https://www.academia.edu/100852276/Classification_of_Software_Systems_attributes_based_on_quality_factors_using_linguistic_knowledge_and_machine_learning_A_review (accessed 10 Jan. 2025).

Ali, M. A., Yap, N. K., Ghani, A. A. A., Zulzalil, H., Admodisastro, N. I., & Najafabadi, A. A. A systematic mapping of quality models for AI systems, software and components. Applied Sciences, 2022, vol. 12, iss. 17, article no. 8700. DOI:10.3390/app12178700.

Danyk, Y., & Vysochanska, V. Technique of testing cyber vulnerabilities and quality of Cyber-physical software systems. Theoretical and Applied Cybersecurity, 2022, vol. 3, iss. 1. DOI: 10.20535/tacs.2664-29132021.1.251314.

Koi-Akrofi, G. Y., Tanye, H., Quist, S. C., Koi-Akrofi, J., Gaisie, E., Agangiba, M., & Yeboah, D. Towards a software quality factor assessment model for learning management systems (LMS). Indian Journal of Science and Technology, 2024, vol. 17, iss. 23, pp. 2463–2468. DOI: 10.17485/ijst/v17i23.1006.

Almogahed, A., Omar, M., Zakaria, N. H., Muhammad, G., & AlQahtani, S. A. Revisiting scenarios of using refactoring techniques to improve software systems quality. IEEE Access, 2023, vol. 11, pp. 28800-28819. DOI: 10.1109/access.2022.3218007.

Mahmud, M. H., Nayan, M. T. H., Ashir, D. M. N. A., & Kabir, M. A. Software Risk Prediction: Systematic Literature Review on Machine Learning Techniques. Applied Sciences, 2022, vol. 12, iss. 22, article no. 11694. DOI: 10.3390/app122211694.

Ali, I., Rizvi, S. S. H., & Adil, S. H. Enhancing Software Quality with AI: A Transformer-Based Approach for Code Smell Detection. Applied Sciences, 2025, vol. 15, iss. 8, article no. 4559. DOI: 10.3390/app15084559.

Nguyen, P. H., Sen, S., Jourdan, N., Cassoli, B., Myrseth, P., Armendia, M., & Myklebust, O. Software engineering and AI for data quality in cyber-physical systems - SEA4DQ'21 workshop report. ACM SIGSOFT Software Engineering Notes, 2022, vol. 47, iss. 1, pp. 26–29. DOI: 10.1145/3502771.3502781.

Oh, H.-S., Kim, D., & Lee, S. Review on the quality attributes of an integrated simulation software for weapon systems. Journal of the Korean Military Science and Technology Society, 2021, vol. 24, iss. 4, pp. 408–417. DOI: 10.9766/kimst.2021.24.4.408.

Jin, W., & Wang, Z. Research and application of quantitative evaluation method based on product quality characteristics. BCP Business & Management, 2022, vol. 17, pp. 84-90. DOI: 10.54691/bcpbm.v17i.374.

Pecorelli, F., Palomba, F., & De Lucia, A. The relation of test-related factors to software quality: A case study on apache systems. Empirical Software Engineering, 2021, vol. 26, article no. 18. DOI: 10.1007/s10664-020-09891-y.

Salomón, S., Duque, R., Bringas, S., & de Oliveira, K. M. Quality-in-Use in practice: A study for context-aware software systems in pervasive environments. Journal of Software: Evolution and Process, 2025, vol. 37, iss. 1, article no. e2764. DOI: 10.1002/smr.2764.

Setiadi, D., Sumitra, T., Karim, A., & Ritzkal. Software quality measurement analysis on academic information systems. Ingénierie des systèmes d'information, 2024, vol. 29, iss. 4, pp. 1453–1460. DOI: 10.18280/isi.290418.




DOI: https://doi.org/10.32620/reks.2025.3.06

Refbacks

  • There are currently no refbacks.