Future Prediction of Urban Real Estate Property Rates Using MATLAB-Based Machine Learning Models

Abstract

Getting real estate property rates right is super important. It helps cities grow in a good way, makes sure we plan buildings and roads well, and shapes how we think about things for the future. Cities are growing super-fast, the economy is all over the place, and everyone wants something different when it comes to property. This makes figuring out what's coming next in the housing market tricky, and the old ways of predicting things just don't cut it anymore. This study introduces a predictive tool, built with MATLAB, that helps estimate future urban real estate prices. It does this by looking at past market information and details unique to each location. We’re using machine learning, specifically regression, to understand how things change over time and what's different structurally from one city area to another. A ten-year dataset collected from rapidly developing urban regions is utilized to validate the model and evaluate prediction consistency. The results demonstrate that the proposed framework effectively captures growth trajectories aligned with infrastructure development and urban expansion patterns. Unlike opaque black-box prediction systems, the MATLAB-based methodology emphasizes interpretability, enabling stakeholders to understand the contribution of key variables influencing property valuation. The findings highlight the practical relevance of AI-assisted forecasting as a decision-support mechanism for urban planners, policymakers, and investors, while maintaining transparency and accountability in data-driven urban governance.