Forecasting Methods for the Real Estate Market: A Review

The significance of the real estate industry to global economies needs accurate forecasting methods for informed decision-making and investment. This literature review comprehensively analyzes the diverse methodologies employed in real estate forecasting, from traditional statistical models such as ARIMA to modern approaches like machine learning. The investigation, spanning literature from 2017–2023, reveals a dynamic landscape of methodologies, each with unique strengths and challenges. While data collection and computing advances have enhanced forecasting capabilities, gaps remain, particularly in integrating unstructured data and combining local and global market factors. The review also emphasizes the evaluation models using metrics, for instance, mean absolute error (MAE), mean squared error (MSE), root mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). The findings highlight the need for continued innovation, interdisciplinary collaboration, and the integration of emerging technologies. Future research should prioritize and combine dynamic model updates, policy-market dynamics, and the integration of real-time data sources. This review represents a collaborative effort between both authors, focusing on methodology development, data analysis, and interpretation.