REAL ESTATE OWNERSHIP TRACKING AND PRICE PREDICTION USING MACHINE LEARNING

This project  presents an integrated web-based platform for real estate price prediction and ownership tracking using machine learning algorithms. The system incorporates comprehensive data preprocessing, feature engineering, and KBest feature selection techniques to optimize predictive performance. Three regression models—Linear Regression (LR), Decision Tree (DT), and Random Forest (RF)—were trained and evaluated on a dataset containing essential property attributes including location, property type, furnishing status, floor details, age, security features, and accessibility metrics. The application features a Flask-based web interface with dual user roles: administrators can manage property listings and predict prices, while registered users can browse properties, submit purchase requests, and make simulated payments. The system implements secure user authentication, request approval workflows, and payment tracking functionality. Model predictions are integrated in real-time during property addition and editing operations. This integrated approach demonstrates the practical applicability of machine learning in real estate valuation while providing a comprehensive platform for property ownership management, enabling accurate price estimation, efficient data management, and streamlined user interactions in a production-ready environment.

Keywords: Real Estate Price Prediction, Machine Learning, Linear Regression, Decision Tree, Random Forest, Flask Framework, Feature Engineering, KBest Feature Selection, Web Application, Property Valuation, Ownership Tracking, Payment Integration, User Authentication