Maternal Health Risk prediction MLOps pipeline

Final Project of the MLOps Zoomcamp hosted by DataTalksClub.

End-to-end platform for training, deploying, and monitoring a churn prediction model—built using MLOps best practices and tools applied from the DataTalksClub MLOps Zoomcamp. Project earned the highest-tier score (achieved by 11 out of 200+ cohort participants) in peer-reviewed project assessment.

Final Project of the MLOps Zoomcamp hosted by DataTalksClub.

End to End toy example of MLOps

Online Prediction Machine Learning System designed, deployed and maintained with MLOps Practices. Goal of the project is to predict individuals income based on census data.

An MLOps pipeline for optimizing game discount strategies using Steam reviews, tags, and competitor pricing. Designed for data-driven revenue maximization in the gaming industry.

No description provided.

MLOps zoomcamp project 2023

MLOps Zoomcamp hosted by DataTalksClub.

This an attempt to predict fraud transactions from a huge collection of records of bank transaction over a period of time.

MLOps Loan Approval Prediction System

Production-grade MLOps pipeline for customer churn prediction with automated training, validation, and serving. Built with Airflow, MLflow, MinIO, Evidently AI, and FastAPI.

Production MLOps pipeline for Paris bike traffic prediction. Airflow orchestration, MLflow tracking (Cloud SQL), FastAPI deployment. Features: automated ingestion, drift detection, champion/challenger models, Prometheus+Grafana monitoring, Discord alerts. 15 Docker services locally.

MLOps Zoomcamp Project

Learn how to handle model drift and perform test-based model monitoring

This is a simple http server to manage feature flags, compatible with Amazon CloudWatch Evidently.

Data drift detection for machine learning using Evidently AI and Valohai. MLOps pipeline: preprocessing, training, drift monitoring and conditional retraining. Python, scikit-learn, California Housing example.

End-to-end MLOps pipeline for multimodal e-commerce product classification (text + image) — ingestion, training, inference and monitoring.

🌎 🚙📚 Predicting travel times and traffic density on a highway in Slovenia

An end-to-end machine learning project predicting DoorDash delivery durations, utilizing MLOps principles and best practices.

This project builds an MLOps pipeline using Evidently for monitoring model performance and Prefect for task orchestration. It processes NYC taxi data, stores metrics in PostgreSQL, and visualizes results in Grafana via Docker Compose.

Agent AI tự động giám sát drift dữ liệu trong pipeline ML, cảnh báo qua email và Slack.

White and Red Wine classification using logistic regression

Build End to End ML pipeline for USVisa prediction, deploy web App to AWS Ec2 instance using Docker, CI/CD with github actions

Comparison between several Python data profile libraries.

Evidently AI in tracking, analyzing, and visualizing machine learning model performance and data drift ensure their reliability over time.

Простенький монолит (кредитный скоринг)

This repository contains a machine learning project focused on building a recommender system. The project is structured to facilitate the development, training, evaluation, and deployment of the recommender model. Key components and configurations are managed using various tools and frameworks.

This project adopts a modular Python architecture within an MLOps framework to enhance subscription renewal predictions, utilizing FastAPI and MongoDB with AWS integration (S3, ECR, EC2). Docker ensures seamless deployment, and GitHub Actions automate the CI/CD workflows. Evidently AI monitors drift to guarantee predictive accuracy and reliability.