Authors

Dr. A. Antony Prakash

Head and Assistant Professor, Department of Information Technology, St. Joseph’s College, Tiruchirappalli, Tamil Nadu, India

Ishwarya C

PG Student, Department of Information Technology, St. Joseph’s College, Tiruchirappalli, Tamil Nadu, India

Praveen Raj S

PG Student, Department of Information Technology, St. Joseph’s College, Tiruchirappalli, Tamil Nadu, India

Abstract

Software development projects often face challenges in managing and resolving a large number of bugs efficiently. Traditional bug tracking systems rely heavily on manual prioritization, which can be time-consuming and prone to human error. This paper surveys artificial intelligence and machine learning approaches for software bug prioritization and prediction. The review considers historical bug-report information such as severity, frequency, affected module, textual descriptions, developer activity, and past resolution time, and examines how these attributes can be used to predict priority levels and identify potentially defect-prone software components. Classification algorithms including Decision Trees, Random Forest, and Support Vector Machines can categorize newly reported bugs into priority classes such as high, medium, and low. Bug-report analysis can additionally use natural-language features to support categorization, severity prediction, and triaging, while software defect prediction models can learn patterns from code and project metrics. Recent literature highlights the usefulness of machine learning while also identifying recurring challenges involving class imbalance, noisy labels, dataset shift, explainability, data quality, and generalization across projects. The paper further presents a unified architecture for an AI-assisted bug management platform using Python, Flask, Scikit-learn, and a relational database. Such a system can combine bug submission, automated priority prediction, defect-risk prediction, history, and reporting in one interface. The survey concludes that AI-assisted bug prioritization can support software maintenance by reducing manual effort and helping teams focus attention on critical issues, while reliable deployment requires representative datasets, rigorous validation, transparent predictions, and human oversight.

Keywords

Artificial Intelligence Machine Learning Software Bug Bug Prioritization Bug Prediction Software Defect Prediction Random Forest Support Vector Machine Software Maintenance

Citation of this Article

Dr. A. Antony Prakash, Ishwarya C, & Praveen Raj S. (2026). A Systematic Review of AI-Driven Software Bug Prediction and Prioritization. Journal of Artificial Intelligence and Emerging Technologies (JAIET). 3(10), 1-6. Article DOI: https://doi.org/10.47001/JAIET/2026.310001

Licence Copyright (c) 2026 Journal of Artificial Intelligence and Emerging Technologies. This work is licensed under a Creative Commons Attribution Non Commercial 4.0 International Licence.

References

  1. F. Matloob et al., “Software Defect Prediction Using Supervised Machine Learning Techniques: A Systematic Literature Review,” Intelligent Automation & Soft Computing, vol. 29, no. 2, pp. 403–421, 2021.
  2. “A systematic literature review on software defect prediction using artificial intelligence: Datasets, Data Validation Methods, Approaches, and Tools,” Engineering Applications of Artificial Intelligence, vol. 111, 104773, 2022.
  3. N. C. Grattan et al., “The need for more informative defect prediction: A systematic literature review,” Information and Software Technology, vol. 171, 107456, 2024.
  4. “An artificial intelligence framework on software bug triaging, technological evolution, and future challenges: A review,” International Journal of Information Management Data Insights, vol. 3, no. 1, 100153, 2023.
  5. G. Long, J. Gong, H. Fang, and T. Chen, “Learning Software Bug Reports: A Systematic Literature Review,” 2025.
  6. A.Daza et al., “Industrial applications of artificial intelligence in software defects prediction: Systematic review, challenges, and future works,” Computers and Electrical Engineering, vol. 124, Part B, 110411, 2025.
  7. “Software Defect Prediction Using Ensemble Learning: A Systematic Literature Review,” IEEE, 2021.
  8. “Software Fault Prediction Using Data Mining, Machine Learning and Deep Learning Techniques: A Systematic Literature Review,” Computers & Electrical Engineering, 2022.
  9. M. A. Olaleye, “Predictive Analytics and Software Defect Severity: A Systematic Review and Future Directions,” Scientific Programming, vol. 2023, article 6221388, 2023
  10. Matloob, F., Aftab, S., Ahmad, M., Khan, M. A., Fatima, A., et al. (2021). Software Defect Prediction Using Supervised Machine Learning Techniques: A Systematic Literature Review. Intelligent Automation & Soft Computing, 29(2), 483–497. DOI: 10.32604/iasc.2021.017562.