Portfolio Details

Each project in this portfolio reflects my hands-on experience in solving real-world problems using data science, machine learning, and full-stack development. From predictive models to intelligent web applications, these solutions are built with a focus on scalability, functionality, and impact.

Project Information

  • Project Name: Car Insurance Prediction
  • Category: MLOps
  • Model Type: Random Forest Regressor
  • Github Repo: Link

Technologies Used

This project showcases an end-to-end MLOps pipeline using tools like FastAPI for model serving, Docker for containerization, and GitHub Actions for CI/CD. The ML model is trained and managed with scikit-learn and pandas, while AWS S3 is used for secure storage of model artifacts and data, versioned using DVC. Infrastructure is hosted on AWS EC2 for scalability.

MLOps Workflow Overview

This project automates the entire ML lifecycle — from raw data ingestion and preprocessing to training, evaluation, and deployment. The pipeline ensures reproducibility and reliability by integrating version control (DVC), automated CI/CD (GitHub Actions), and cloud-based deployment (AWS EC2 & S3). Each new model iteration is containerized with Docker and can be automatically pushed live through CI/CD pipelines.

This modular MLOps setup makes the system production-ready, enabling scalable updates, secure storage, and maintainable architecture. Future upgrades also support integration of Prometheus and Grafana for real-time monitoring and logging.

MLOps Stack Highlights

  • GitHub Actions for automated testing, retraining, and deployment
  • Docker for packaging and consistent cross-environment deployment
  • AWS EC2 & S3 for hosting and storage
  • IAM-controlled access for secure model and data management
  • DVC for data and pipeline versioning
  • FastAPI for serving the model through RESTful APIs

This project emphasizes robust MLOps implementation by combining automation, scalability, and cloud-native deployment — enabling smooth transitions from experimentation to production.