Automated Testing Strategies for Machine Learning Models in DevOps Pipelines
DOI:
https://doi.org/10.15662/IJEETR.2023.0503005Keywords:
Automated Testing, Machine Learning Models, DevOps Pipelines, Continuous Integration, Data Quality, Model Accuracy, Performance Metrics, Testing Strategies, Validation, Reliability, Robustness, Deployment, Quality Assurance, Software Development, Production EnvironmentsAbstract
Automated Testing Strategies for Machine Learning Models in DevOps Pipelines address the critical need for reliable and efficient testing methods in the context of deploying machine learning models. This paper explores the challenges and opportunities of integrating automated testing into DevOps pipelines for machine learning applications. It examines the unique requirements of testing machine learning models, such as data quality, model accuracy, and performance metrics, and proposes strategies for implementing automated testing practices to ensure the robustness and reliability of machine learning deployments. By analyzing best practices, tools, and techniques for automated testing in the context of DevOps pipelines, this paper aims to provide insights for organizations looking to optimize their testing processes and enhance the quality of their machine learning applications in production environments
References
. S. Amershi, A. Begel, C. Bird, R. DeLine, H. Gall, E. Kamar, N. Nagappan, B. Nushi, and T. Zimmermann.
Software engineering for machine learning: A case study. In Proc. ICSE, 2019.
[2]. S. Banerjee, S. Chakraborty, A. K. Debnath, and R. N. Mahapatra. DevOps for machine learning. IEEE Software, 36(6):100–107, 2019.
[3]. S. Basiri, J. N. Amaral, and L. C. Briand. Machine learning in software testing: A bibliographic survey.
ArXiv, abs/2006.10232, 2020.
[4]. N. Botezatu, M. Mircea, and R. Marinescu. Machine learning models in DevOps: A systematic literature review. In Proc. SEKE, 2020.
[5]. Y. Chen, D. Drachsler-Cohen, and T. Menzies. A literature review on the use of machine learning in software testing. In Proc. ASE, 2018.
[6]. L. Cicchetti and F. Qureshi. A survey on machine learning in DevOps. In Proc. ICSE-SEIP, 2020.
[7]. M. D. Ernst, R. Belli, and B. S. Meyer. Machine learning for DevOps: A systematic mapping study. ArXiv, abs/2006.05244, 2020.
[8]. A. G. R. Fernandes and A. M. Simão. Machine learning in continuous integration and continuous deployment pipelines: A mapping study. In Proc. SAC, 2020.
[9]. D. Gavran, D. M. R. Filho, and U. Kulesza. Machine learning for DevOps: A systematic literature review. In Proc. EASE, 2019.
[10]. E. Guzman, S. McIntosh, and A. E. Hassan. A machine learning approach for DevOps knowledge sharing.
Emp. Soft. Eng., 24(3):1561–1590, 2019.
[11]. S. Hovsepyan, V. Garousi, and I. Macia. Machine learning in software testing and quality assurance: A systematic mapping study. In Proc. QSIC, 2019.
[12]. J. J. Jiang, B. H. Ren, and S. T. Xie. A survey of machine learning in software testing. J. Syst. Soft., 154:103- 117, 2019.
[13]. Y. Li, B. Xie, and L. Zhang. A comprehensive survey of machine learning in DevOps. In Proc. ICSE, 2020. [14]. M. Linares-Vásquez, G. Bavota, C. Bernal-Cárdenas, R. Oliveto, and D. Poshyvanyk. How to effectively use
topic models for software engineering tasks? An approach based on genetic algorithms. In Proc. ICSME, 2018.
[15]. N. Meng, Y. Zhou, and D. Lo. A survey of machine learning in software testing. ACM Comput. Surv., 51(1):1–35, 2018.
[16]. P. Morrison, T. V. Pham, and A. M. Memon. Machine learning in software testing: State of the art and future directions. In Proc. ASE, 2018.
[17]. S. M. M. Rahman, Y. Z. Li, and C. K. Roy. Machine learning for DevOps: A systematic mapping study. In Proc. ICSE, 2019.
[18]. C. Zhang, H. Zhang, and B. Xie. Machine learning in DevOps: A systematic mapping study. ArXiv, abs/2006.05780, 2020.
