CLOUD-NATIVE MLOPS FRAMEWORK FOR PRODUCTIONSCALE HEALTHCARE CLAIMS ANALYTICS

Abstract

Healthcare claims analytics has become increasingly complex due to the massive growth of digital healthcare data, evolving reimbursement policies, fraud risks, and the need for accurate financial and operational decisionmaking. Traditional analytics approaches often struggle with scalability, model deployment, continuous monitoring, and real-time processing of large-scale healthcare claims datasets. This paper proposes a cloud-native MLOps framework for production-scale healthcare claims analytics by integrating machine learning, cloud computing, container orchestration, automated machine learning pipelines, data engineering, predictive analytics, and continuous model governance. The proposed methodology enables automated data ingestion, feature engineering, model training, deployment, monitoring, and lifecycle management for healthcare claims intelligence. Experimental evaluation demonstrates improvements in claims prediction accuracy, fraud detection capability, scalability, deployment efficiency, operational reliability, and healthcare decision support. The proposed framework provides a secure and scalable solution for intelligent healthcare claims management while supporting modern healthcare organizations in achieving data-driven transformation. Keywords— Cloud-Native MLOps, Healthcare Claims Analytics, Machine Learning, Predictive Analytics, Kubernetes, Model Governance, Healthcare AI, Data Engineering.