Paper Title
Revolutionizing Real Estate Investment: Advanced Machine Learning-Based Model for Price Prediction in Data-Limited Markets

Abstract
The real estate market plays a crucial role in urban economic development, particularly in emerging cities like New Cairo, Egypt. This study focuses on predicting real estate prices by analyzing the impact of property-specific attributes using advanced machine learning techniques, including XGBoost, LightGBM, Random Forest, and Decision Tree models. These methods address the inherent complexity of real estate markets by capturing non-linear relationships and leveraging detailed property data. Through rigorous modeling and hyperparameter tuning, the study identifies the most influential features affecting property prices and compares the performance of different models. The findings demonstrate that XGBoost and LightGBM outperform other models, achieving the highest accuracy in price prediction, with R² values of 0.8345 and 0.8253, respectively. These results offer actionable insights for investors, developers, and policymakers, contributing to more informed decision-making and sustainable urban development in rapidly growing markets. Keywords - Real estate price prediction, machine learning, XGBoost, LightGBM, New Cairo, property-specific attributes, emerging markets, sustainable urban development.