MODEL FOR ASSESSING THE RISK OF DEFECTS IN SOFTWARE COMPONENTS OF DISTRIBUTED COMPUTER SYSTEMS
DOI:
https://doi.org/10.26906/SUNZ.2026.2.271Keywords:
distributed computer system, prediction, machine learning, automated testing, defect risk assessment, metrics, CatBoost, quality analysis, deep learning, multicomponent systemAbstract
Relevance . The relevance of the study is determined by the need to improve the efficiency of automated testing of software in distributed computer systems, which are characterized by a complex structure, dependencies between components, and an increased risk of defects. Existing approaches to defect prediction mostly do not provide comprehensive consideration of the structural characteristics of components, the intensity of their changes, and the parameters of test execution, which complicates the justified planning of testing. Therefore, the development of a model for assessing the risk of defects in software components of distributed computer systems to support the process of prioritizing automated testing is relevant. This makes it possible to focus testing resources on the most critical software components and thereby increase the overall effectiveness of software quality control. The object of research is the process of detection and assessment of defects in software components of distributed computer systems in the context of automated testing. Purpose of the article is to develop a model for assessing the risk of defects in software components of distributed computer systems to improve the efficiency of automated testing. Research results. In this work, a model for assessing the risk of defects in software components of distributed computer systems has been developed, which makes it possible to form an integral defectiveness indicator based on the structural characteristics of the program code and the results of automated testing. Experimental studies using machine learning algorithms have shown that the best results are provided by the CatBoost model, which demonstrated the highest values of ROC–AUC and Precision–Recall characteristics compared to other investigated approaches. The results obtained confirm the possibility of effectively ranking software components by the level of defect risk and using this information for the prioritization of automated testing in distributed computer systems.Downloads
References
1. Jalaj Pachouly, Swati Ahirrao, Ketan Kotecha, Ganeshsree Selvachandran, Ajith Abraham. A systematic literature review on software defect prediction using artificial intelligence: Datasets, Data Validation Methods, Approaches, and Tools, Engineering Applications of Artificial Intelligence, Volume 111, 2022. P. 1–33. https://doi.org/10.1016/j.engappai.2022.104773.
2. Szymon Stradowski, Lech Madeyski. Machine learning in software defect prediction: A business-driven systematic mapping study. Information and Software Technology,Volume 155,2023. P. 1–17. https://doi.org/10.1016/j.infsof.2022.107128.
3. Görkem Giray, Kwabena Ebo Bennin, Ömer Köksal, Önder Babur, Bedir Tekinerdogan. On the use of deep learning in software defect prediction. Journal of Systems and Software, Volume 195, 2023. P. 1–26. https://doi.org/10.1016/j.jss.2022.111537.
4. Zuhaira Muhammad Zain, Sapiah Sakri, and Nurul Halimatul Asmak Ismail. Application of Deep Learning in Software Defect Prediction: Systematic Literature Review and Meta-analysis. Inf. Softw. Technol. Volume 158, 2023. https://doi.org/10.1016/j.infsof.2023.107175.
5. Abdu A, Zhai Z, Algabri R, Abdo HA, Hamad K, Al-antari MA. Deep Learning-Based Software Defect Prediction via Semantic Key Features of Source Code–Systematic Survey. Mathematics. 10(17):3120. 2022. P. 1–26. https://doi.org/10.3390/math10173120.
6. Natalie Grattan, Daniel Alencar da Costa, Nigel Stanger. The need for more informative defect prediction: A systematic literature review. Information and Software Technology. Volume 171, 2024. P. 1-24. https://doi.org/10.1016/j.infsof.2024.107456.
7. Marijan, D. Comparative study of machine learning test case prioritization for continuous integration testing. Software Qual J 31. 2023. P. 1415–1438. https://doi.org/10.1007/s11219-023-09646-0.
8. Peng Tang, Junfeng Wang, Mingxing Liu. Variational learning to rank for Test Case Prioritization via prioritizing metric inspired differentiable loss. Engineering Applications of Artificial Intelligence. Volume 141. 2025. https://doi.org/10.1016/j.engappai.2024.109776.
9. Tapas Kumar Choudhury, Mousumi Behera, Sanjit Kumar Dash, Subhendu Kumar Pani, Jibitesh Mishra, AnoLSTM-A Deep Learning Approach for Test Cases Prioritization, Procedia Computer Science, Volume 258.2025. Pages 1793-1803. https://doi.org/10.1016/j.procs.2025.04.431.
10. Md Arfan Uddin, Shakthi Weerasinghe, Darek Gajewski, Melika Akbarsharifi, Roxana Akbarsharifi, Christopher Stoner, Tomas Cerny, Sen He. Microservice logs analysis employing AI: A systematic literature review, Journal of Systems and Software. Volume 236.2026. P.1-93. https://doi.org/10.1016/j.jss.2026.112786.
11. S. Alhusain, "Predicting Relative Thresholds for Object Oriented Metrics," 2021 IEEE/ACM International Conference on Technical Debt (TechDebt), 2021, pp. 55-63, doi: 10.1109/TechDebt52882.2021.00015.
12. Robredo, M., Esposito, M., Taibi, D., Peñaloza, R., & Lenarduzzi, V. SQuaD: The Software Quality Dataset - Dataset [Data set]. Zenodo. 2025. https://doi.org/10.5281/zenodo.17566691.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Dmytro Diachenko, Vladyslav Diachenko
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
