Test automation is vital for software release in modern times, it often results in false positives due to failed tests, which leads to the waste of precious engineer's time and, hence, loss of trust in the system. The proposed research project seeks to design a predictive model that can estimate the possibility of false positive failure before test automation. Our model was trained using the data on 12,400 test cases from 840 automated tests that were conducted during 18 months of continuous integration process. In total, there were 42 features selected as input data for training – they include data from logs, information about code changes, environmental factors, and failure history. Five machine learning algorithms were tested, XGBoost algorithm being the most successful with accuracy being 91.2%, while F1-score equalled 90.5%. Testage, code churn, and failure rate were the most important features. After deploying our tool into production CI pipeline, we noticed a reduction inthe number of test cycles of up to 34% as well as increase of defect detection speed by 60%.
Gitanjali Kumari, M. K. Shukla, Nawnit Kumar et al.· 2026 6th International Confe...· 0 citations
In Ensuring fast and precise code review process has become one of the major problems of the modern DevOps world, where software development happens quickly for code reviews to be done manually. In this paper, we introduce a novel automated code review framework named AICR-DevOps, which utilizes a combination of rule-based static analysis, fine-tuned CodeBERT semantic classifier, and large language model using confidence-based aggregation. The framework architecture allows successfully combining the power of traditional program analysis approaches and artificial intelligence reasoning capabilities to achieve high review accuracy with minimized false positives. Together with GitHub Actions, the framework is capable of conducting pull request analysis instantly and constantly adapting to specific coding practices of projects by fine-tuning based on developer feedback using LoRA method. Experimentation with the proposed framework on 12,400 pull requests gathered from 40 Java and Python repositories reached 84.7% precision, 81.3% recall, and an F1-score of 82.9%, with review comments provided in 38 seconds on average. Moreover, a controlled study conducted with 48 developers showed that the acceptance rate of the developers to the framework reached 73.6%.
Nawnit Kumar, M. K. Shukla, Raushendra Kumar et al.· 2026 6th International Confe...· 0 citations