🏡 House Price Prediction Web App

---

🧠 Project Overview

The House Price Prediction Web App is a full-stack data science project that predicts home prices based on input features such as location, square footage, number of bedrooms (BHK), and bathrooms.

The project combines:

• 🧮 Machine Learning Model trained on real estate data
• ⚙️ Flask Backend for serving predictions via REST API
• 💻 Modern Frontend built with HTML, CSS, and JavaScript

---

✨ Features

✅ Predict house prices instantly using ML model
✅ Clean and responsive glassmorphism UI
✅ Location options dynamically loaded from Flask API
✅ Smooth transitions and hover animations
✅ Error handling and validation for user input

---

🧩 Tech Stack

Layer	Technologies Used
Frontend	HTML, CSS, JavaScript, jQuery
Backend	Flask (Python)
Machine Learning	scikit-learn, pandas, NumPy
Model Deployment	Pickle serialization
Visualization	Matplotlib / Seaborn (for analysis phase)

---

🏗️ Project Structure

📦 House Price Prediction Web App
├── 📁 client/                # Frontend (HTML, CSS, JS files)
│   ├── app.css
│   ├── app.js
│   └── index.html
│
├── 📁 model/                 # Machine Learning model files
│   ├── house_prices_model.pkl
│   └── columns.json
│   └── main.ipynb
│
│
├── 📁 server/                # Flask backend server
│   ├── main.py
│   └── util.py
│
├── 📁 venv/                  # Virtual environment (ignored by Git)
│
├── .gitignore
├── requirements.txt          # Python dependencies
└── README.md

2️⃣ Install Dependencies

Make sure you have Python 3.8+ installed.

pip install -r requirements.txt

3️⃣ Run the Flask Server

python app.py

4️⃣ Open the Frontend

http://127.0.0.1:5000/

🧮 Example Prediction

| Input    | Value              |
| -------- | ------------------ |
| Location | talaghattapura
| Area     | 2000 sq.ft         |
| BHK      | 1                  |
| Bath     | 2                  |

✅ Predicted Price: ₹128.89 Lakh

📚 How It Works

1. User Input: The user enters area, BHK, bathrooms, and selects a location.

2. Frontend Request: The frontend sends data to Flask API endpoint /predict_home_price.

3)Model Processing: Flask loads the trained model (house_prices_model.pkl) and predicts the price.

4)Response Display: The predicted price is returned and displayed dynamically in the UI.

💡 Future Improvements

1. 🏘️ Add city-wide filtering and price comparison

2. 📈 Include graphs for area vs price trends

3. 🧠 Experiment with advanced ML models (XGBoost, Random Forest)

4. ☁️ Deploy the project using AWS / Render / Heroku

❤️ Acknowledgments

💻 Flask                → For building a lightweight and efficient backend API
🧠 scikit-learn         → For developing and training the house price prediction model
🔤 Google Fonts (Inter) → For clean and modern typography in the frontend
🎨 CSS Glassmorphism    → For the elegant and translucent user interface design

📧 Contact

👨‍💻 Developer : Abinan
🌐 GitHub     : https://github.com/ABINAN2011
📩 Email      : k.abinan20@gmail.com