End-to-end MLOps platform for customer churn prediction featuring feature stores, model versioning, API serving, and automated workflows
-
Updated
Nov 29, 2025 - Jupyter Notebook
End-to-end MLOps platform for customer churn prediction featuring feature stores, model versioning, API serving, and automated workflows
Production-grade real-time fraud detection system for fintech transactions. Built with FastAPI, containerized via Docker, deployed on GKE with autoscaling, monitored using OpenTelemetry, and secured against data poisoning attacks. Includes CI/CD pipelines, MLflow experiment tracking, DVC data versioning, and fairness/explainability audits.
A Tutorial on credit risk feature store building
Add a description, image, and links to the feast-feature-store topic page so that developers can more easily learn about it.
To associate your repository with the feast-feature-store topic, visit your repo's landing page and select "manage topics."