Machine learning algorithms on price and rent predictions in real estate: A systematic literature review / Muhamad Harussani Abdul Salam ... [et al.]

Valuers face various challenges in determining property prices and rental values due to dependence on market data. Lack of data means lack of support for valuable contributions of property value attributes. The use of existing databases in property valuation assignments presents intrinsic challenges as the valuer could derive incorrect assumptions when analysing value-issued comparable data. The introduction and observation of the Machine Learning Model to solve unforeseen issues are timely in Industrial Revolution 4.0. It is part of the modern scientific methodology which offers an automated procedure for prediction and classification of circumstances. Malaysian real estate markets are yet to embrace machine learning techniques for property analysis. It is worth noting that when predicting property values and rentals, appraisers and investors cannot rely on historical market data from real estate transactions. To meet this requirement, certain computing techniques optimised for handling large amounts of data are the best options. This paper presents the machine learning algorithm applications on the prediction of property prices and rents in real estate. This study adapts a systematic literature review on features that influence office building rentals in accordance with the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA). The systematic review findings suggest that Random Forest (RF), Decision Tree (DT), Linear Regression (LR), and Support Vector Machine (SVM), frequently utilise Machine Learning in price and rent predictions. This study will provide new insights on the Machine Learning Algorithms in the real estate industry.