arXiv subjects

Keerthiga Rajenthiram

Publications and source records attributed to Keerthiga Rajenthiram.

3 recordsLinked to original sources

arXiv2026

Architecturally Significant MLOps Guidelines for ML Model Integration and Deployment: a Gray Literature Review

Context. Despite the growing adoption of Machine Learning Operations (MLOps), teams often approach MLOps projects in an ad hoc manner due to the lack of consolidated architectural guidance. The community would benefit from a reference that synthesizes knowledge to inform the architectural design of MLOps systems, especially regarding the integration and deployment of ML models. Objective. In response, our goal is to provide a comprehensive overview of architecturally significant guidelines for the integration and deployment of ML models in MLOps systems. Method. We conduct a gray literature review of 103 web sources to analyze state-of-practice knowledge on MLOps model integration and deployment. We then apply thematic analysis to synthesize these practices into recommended guidelines. Results. We contribute a collection of 25 architecturally significant MLOps guidelines for model integration and deployment, organized into five categories, and describe their impact on the overall system architecture. Conclusion. Our results serve as an overview of state-of-practice MLOps guidelines to support researchers and practitioners with the integration and deployment of ML models in their MLOps systems.

cs.SE↗

arXiv2026

A Systematic Review of MLOps Tools: Tool Adoption, Lifecycle Coverage, and Critical Insights

Machine Learning Operations (MLOps) has become increasingly critical as more organisations move ML models into production. However, the growing landscape of MLOps solutions has introduced complexity for practitioners trying to select appropriate tools. To investigate how and why these tools are adopted in practice, this paper conducts a systematic review of the academic literature focused on MLOps tools. We map tools to MLOps lifecycle components to reveal their function, scope, and the challenges they are designed to address. We identify usage trends and synthesise reported benefits and limitations. The most commonly used components, according to the findings, are orchestration frameworks, data versioning, experiment tracking, and managed cloud platforms. No single tool covers the entire lifecycle, so researchers often combine multiple tools to build complete pipelines. This highlights the importance of interoperability across MLOps tools in real-world MLOps pipelines.

cs.SE↗

arXiv2025

Towards Continuous Experiment-driven MLOps

Despite advancements in MLOps and AutoML, ML development still remains challenging for data scientists. First, there is poor support for and limited control over optimizing and evolving ML models. Second, there is lack of efficient mechanisms for continuous evolution of ML models which would leverage the knowledge gained in previous optimizations of the same or different models. We propose an experiment-driven MLOps approach which tackles these problems. Our approach relies on the concept of an experiment, which embodies a fully controllable optimization process. It introduces full traceability and repeatability to the optimization process, allows humans to be in full control of it, and enables continuous improvement of the ML system. Importantly, it also establishes knowledge, which is carried over and built across a series of experiments and allows for improving the efficiency of experimentation over time. We demonstrate our approach through its realization and application in the ExtremeXP1 project (Horizon Europe).

cs.SE↗