end-to-end-ml

AI-powered medical imaging system for multi-disease chest X-ray detection,built with EfficientNet deep learning, a FastAPI backend, and an interactive Streamlit dashboard. Deployed on Render for real-time healthcare diagnostics, detecting conditions like Atelectasis, Edema and more.An end-to-end project demonstrating model training,API development.

An end-to-end regression project trained on the Boston Housing dataset, featuring data analysis, Random Forest modeling, model evaluation, and real-time prediction through a REST API built with FastAPI.

An end-to-end MLOps project using Python, GitHub Actions, and Evidently AI to automate model monitoring, drift detection, and retraining.

An end-to-end Machine Learning application that predicts insurance premium categories based on customer demographics, lifestyle factors, health indicators, and financial information.

End-to-end machine learning classification pipeline on the Breast Cancer Wisconsin dataset featuring leakage-free preprocessing, GridSearchCV tuning, model evaluation, and SHAP explainability.

End-to-end MLOps Facial Emotion Recognition app with ViT, Gradio UI, and CI/CD deployment on Hugging Face Spaces.

An ML-powered house price estimator with a FastAPI backend and React frontend.

An end-to-end machine learning project built on the UCI Heart Disease dataset, covering data preprocessing, feature engineering, model training, evaluation, and deployment. The project includes Streamlit app that supports both single-patient and batch predictions, ensuring reproducibility through a well-structured pipeline and saved model artifacts

A Python-based handwritten character recognition system that uses a CNN trained on self-collected data to accurately recognize mouse-drawn characters. Includes a unified desktop UI for real-time prediction, dataset management, and model retraining.

🌸 A production-ready Machine Learning web app that classifies Iris flower species using K-Nearest Neighbors (KNN). Built with Streamlit, Scikit-learn, and deployed for real-time predictions with interactive model tuning and evaluation metrics.

Production-ready ML model predicting DoorDash delivery times.

End-to-end ML pipeline with systematic model selection, MLflow experiment tracking on DagsHub, and live Hugging Face deployment. Random Forest AUC=0.921. CI/CD via GitHub Actions.

A production-grade, end-to-end MLOps platform designed to automate the complete lifecycle of a financial fraud detection system. This repository demonstrates how to transition from a static ML model to a self-healing, automated production system.

End-to-End Hybrid Music Recommender System combining Content-Based & Collaborative Filtering on 50K+ Spotify songs & 9.7M user interactions. Dask-powered large-scale data processing, DVC pipeline versioning, Streamlit UI with Spotify audio previews, Docker containerization, CI/CD pipeline (GitHub Actions→AWS ECR), Deployed on EC2

End-to-end ML system to predict student dropout risk. Gradient Boosting (88% acc, 96.6% AUC) + FastAPI backend + real-time web UI.

An interactive Streamlit ML platform to upload datasets, train multiple classification models, compare performance metrics, and visualize ML results.

End-to-end ML pipeline to predict student academic performance using Scikit-learn, feature engineering, and modular production-style architecture.

End-to-end MLOps project for predictive maintenance using engine sensor data. Includes data versioning on Hugging Face, MLflow experiment tracking, CI/CD with GitHub Actions, and Dockerized Streamlit deployment for real-time engine failure classification.

An end-to-end Customer Churn Prediction project built using Machine Learning, FastAPI, and Streamlit. The model predicts whether a telecom customer is likely to churn based on factors such as tenure, contract type, internet service, payment method, monthly charges, and total charges. The project includes model training, backend API integration, and