🏡 Boston House Price Predictor

An elegant machine learning application for real-time Boston housing price predictions

✨ Live Demo : https://boston-houseprice-prediction-g32w.onrender.com/

Precision forecasting meets beautiful design

---

📊 Overview

graph LR
    A[User Input] --> B[Flask API]
    B --> C[Trained Model]
    C --> D[Price Prediction]
    D --> E[Visual Result]
    style A fill:#ff6b6b
    style E fill:#51cf66

Loading

This application transforms 13 housing features into accurate price estimates using a sophisticated Linear Regression model. Built with precision and designed with elegance, it bridges data science with practical application.

✨ Features

🎯 Real-time Prediction

Instant results with sub-second response time

📈 Accurate Model

Trained on comprehensive Boston housing data

🚀 Production Ready

Deployed and optimized for real-world use

---

🏗️ Architecture

# Core Prediction Flow
Input Features → Data Validation → Model Inference → Result Formatting → Beautiful Output

🛠️ Technology Stack

Layer	Technology	Purpose
Frontend	HTML5, CSS3, JavaScript	User Interface & Experience
Backend	Python Flask, REST API	Server Logic & Routing
ML Engine	Scikit-learn, Linear Regression	Price Prediction
Data	Pandas, NumPy	Data Processing
Deployment	Render	Production Hosting
Version Control	Git, GitHub	Code Management

📁 Project Structure

Boston_HousePrice_Prediction-/
├── 📊 house_price_analysis.ipynb     # Complete EDA & Model Training
├── 🤖 house_price_analysis.pkl       # Serialized Trained Model
├── 🚀 app.py                         # Flask Application Entry Point
├── 📋 requirements.txt               # Dependency Management
├── 🎨 templates/
│   └── index.html                    # Interactive Web Interface
└── 📈 BostonHousing.csv              # Training Dataset (506 samples)

---

🚀 Quick Installation

1. Clone & Setup

# Clone repository
git clone https://github.com/24f2004698/Boston_HousePrice_Prediction-.git

# Navigate to project
cd Boston_HousePrice_Prediction-

# Create virtual environment
python -m venv venv

# Activate environment
source venv/bin/activate  # Windows: venv\Scripts\activate

2. Install Dependencies

pip install -r requirements.txt

3. Launch Application

python app.py

🔗 Access at: http://localhost:5000

---

🎮 Usage Guide

1. Access the application via Live Demo or localhost
2. Input the 13 Boston housing features:
   • Location Factors: CRIM, ZN, INDUS
   • Property Details: CHAS, NOX, RM
   • Community Metrics: AGE, DIS, RAD, TAX
   • Education & Demographics: PTRATIO, B, LSTAT
3. Click the Predict button
4. View your instant price estimate with visual feedback

---

📊 Model Performance

The Linear Regression model was trained on the BostonHousing.csv dataset, achieving optimal performance through:

• Feature Selection: 13 most impactful housing metrics
• Data Preprocessing: Normalized and cleaned inputs
• Validation: Rigorous testing for reliability
• Persistence: Model saved for immediate inference

---

🌐 Live Deployment

Status: ✅ Active

---

📬 Connect

Found this project useful? Give it a ⭐ on GitHub!

---

Built with ❤️ using Python & Flask
Data Science • Web Development • Real Estate Analytics