🏠 Real Estate Price Prediction using PySpark ML

A Big Data Analytics project that predicts residential property prices in Indian cities using various machine learning algorithms.

🎯 Overview

This project analyzes a large dataset of residential properties from major Indian cities and implements different regression models to predict property prices based on various features.

🔧 Models Implemented

• 🌲 Random Forest Regression
• 📈 Linear Regression
• 🌳 Decision Tree Regression
• 🚀 Gradient Boosted Tree Regression

✨ Key Features

• Comprehensive data preprocessing and cleaning
• Feature selection using Chi-Square test
• Outlier detection and handling
• Model performance comparison and visualization
• Property price prediction for new inputs

📊 Performance Metrics

• RMSE (Root Mean Square Error)
• MSE (Mean Square Error)
• MAE (Mean Absolute Error)
• R² Score

🏆 Best Performing Model

The Gradient Boosted Tree (GBT) Regression showed the best performance with:

• R² Score: 0.74
• Lowest RMSE: 0.032
• Lowest MAE: 0.009

🛠️ Technologies Used

• PySpark ML
• Pandas
• Matplotlib
• Seaborn
• Plotly

Research Paper of the Project

📑 "Real Estate Price Prediction Using PySpark MLlib"

• Published in: 2024 IEEE International Conference on Smart Power Control and Renewable Energy (ICSPCRE)
• DOI - https://doi.org/10.1109/ICSPCRE62303.2024.10675142

👥 Collaborators

Name	GitHub
Prajwal	@pk24100

📝 License

This project is licensed under the Creative Commons BY-NC 4.0 - see the LICENSE.txt file for details.

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.