Boston Housing Price Prediction

Web app predicts Boston house prices with Decision Tree ML. Flask backend, REST API, live demo inputs & full data analysis. Production model, modern UI, 78.8% R² accuracy.

Overview

A machine learning web application that predicts Boston house prices using Decision Tree regression. The platform features a Flask backend with REST API endpoints, allowing users to input property features and receive instant price predictions. The application includes comprehensive data analysis capabilities and a modern, user-friendly interface.

Challenge

House prices depend on many interacting features (location, rooms, age, tax rate). The task was to build an interpretable regression model on the Boston Housing data and expose it through an API so users can get instant estimates from their own inputs.

Solution

Decision Tree Regressor served through a Flask REST API with live demo inputs and data analysis UI.

Architecture

scikit-learn Decision Tree · Flask REST API · Pandas / NumPy analysis · Railway deployment

Results

  • R² Score: 78.8%
  • Dataset Size: 506 samples
  • Features: 13
  • Achieved 78.8% R² accuracy on Boston housing data
  • Production-ready Flask REST API
  • Real-time price prediction interface
  • Comprehensive data analysis dashboard
  • Deployed on Railway for public access

Technologies

  • Python
  • Flask
  • scikit-learn
  • Pandas
  • REST API
  • Railway

All projects · Contact

Loading project…