Experimentation, deployment and monitoring Machine Learning models: Approaches for applying MLOps

TL;DR

The paper tackles the challenges of publishing and operating ML workflows in production by arguing for an integrated MLOps pipeline with three core stages: Experimentation, Deployment, and Model Monitoring. It surveys literature to justify automation, reproducibility, and governance, and illustrates the approach with three industry case studies—Financial Services, Tech Solution Providers, and Energy Consumption Prediction—demonstrating practical MLOps architectures and benefits. The contributions include a structured lifecycle framework, a discussion of deployment and monitoring hurdles, and evidence that MLOps enhances speed, reliability, transparency, and security in production environments. Overall, the work emphasizes operationalizing ML with governance, observability, and continuous delivery to enable scalable, accountable AI systems in industry.

Abstract

In recent years, Data Science has become increasingly relevant as a support tool for industry, significantly enhancing decision-making in a way never seen before. In this context, the MLOps discipline emerges as a solution to automate the life cycle of Machine Learning models, ranging from experimentation to monitoring in productive environments. Research results shows MLOps is a constantly evolving discipline, with challenges and solutions for integrating development and production environments, publishing models in production environments, and monitoring models throughout the end to end development lifecycle. This paper contributes to the understanding of MLOps techniques and their most diverse applications.