REAL ESTATE INVESTEMENT TRUSTS

Abstract

Real Estate Investment Trusts (REITs) play a pivotal role in democratizing real estate investment by allowing individuals and institutions to invest in income-generating properties without owning them directly. Traditionally, REIT performance evaluation relies on historical financial ratios, macroeconomic indicators, and property market trends. However, in today’s data-driven financial landscape, these static methods are often insufficient to capture the complex, nonlinear dynamics influencing REIT performance. This study proposes an AI-powered framework that employs Machine Learning (ML) and Deep Learning (DL) techniques to forecast REIT returns, analyze risk factors, and enhance decision-making accuracy for investors and fund managers. Using historical REIT data, interest rates, inflation, rental yields, and economic indicators, the study applies ML models such as Random Forests, Support Vector Regression (SVR), and Gradient Boosting to identify key performance drivers and predict short- and long-term returns. Additionally, Deep Learning models—especially Long Short-Term Memory (LSTM) networks—are utilized to capture time-dependent patterns and forecast REIT prices with greater precision. The integration of these intelligent systems enables continuous learning and adjustment, empowering stakeholders with real-time insights into asset performance, market volatility, and portfolio optimization.This AI-augmented REIT analysis framework not only improves the reliability of investment forecasting but also transforms traditional real estate finance by bringing agility, scalability, and strategic intelligence into REIT evaluation. The findings of this research have the potential to shape smarter
investment strategies and strengthen the risk management capabilities of real estate
investors in a rapidly evolving market environment.