Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{205045,
        author = {Mollety Dwaraka Venkata Naga Srikanth and Prathyusha Gali},
        title = {Machine Learning-Based Anomaly Detection in CI/CD Pipelines for Reliable DevOps Automation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {7611-7617},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=205045},
        abstract = {Continuous integration and continuous deployment (CI/CD) pipelines are vital tools in the DevOps tool box, issues like build failures, resource constraints, and deployment issues can lower system reliability and efficiency. This study proposes a novel framework called Anomaly Detection Framework using Machine Learning for enhancing the reliability of DevOps Automation. The steps of the methodology include data collection from the CI/CD Pipeline Failures Dataset for AIOps, data preprocessing, feature extraction, detection of anomalies, model training, and performance evaluation. The four machine learning models implemented and tested were Isolation Forest, Local Outlier Factor (LOF), Random Forest and Autoencoder. The experimental results showed that Random Forest model showed the highest accuracy, 96.3%, and precision, 95.6%, recall, 96.8%, and F1 score 96.2%. Further, the anomalous pipeline executions resulted in peaks of 90% and 85% CPU and memory utilization, respectively. The results show that machine learning algorithms can accurately identify anomalies, minimize operational risks, and markedly improve the reliability and efficiency of the CI/CD-driven DevOps automation.},
        keywords = {Machine Learning, Anomaly Detection, CI/CD Pipelines, DevOps Automation, Predictive Analytics, Software Reliability.},
        month = {June},
        }