Machine Learning Applications in Real Estate: Critical Review of Recent Development

Abstract

Machine learning (ML) and deep learning (DL) methods have recently become a hot topic in the real estate discipline. They have contributed to the advancement of various domains in real estate sector. This paper provides a critical review of recent trends in applying machine learning and deep learning (ML/DL) techniques in various domains of real estate and investigate their potential for the real estate sector. Recent advances in model development, testing and areas of application in real estate in the past 4 years (2017–2020) are presented. Findings reveal that 20 different ML and DL algorithms were utilized to examine various aspects of real estate development and valuation, and that the most commonly used algorithms are neural networks, regression models, random forest, booting, support vector machine and cubist/pruned model tree.