Abstract
Machine learning algorithms commonly outperform the traditional hedonic models in property valuation; however, it is hard to capture the inner workings of these complex models due to their black-box nature. To address the opaqueness of ML models, this study applies model-agnostic interpretability methods at the both global and local levels for a Random Forest model which provided better prediction accuracy than Support Vector Machines and eXtreme Gradient Boosting algorithms in predicting residential property prices. The results of this study suggest that interpretable ML methods can bring transparency to opaque ML models, and visualize feature effects and interactions in property valuation models.
Acknowledgements
The author would like to thank two anonymous referees for their valuable comments and suggestions.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Declarations
The research presented in the manuscript is original and has not been published elsewhere and is not under consideration by another journal. I have no financial or proprietary interests in any material discussed in this article.
Additional information
Notes on contributors
Tugba Gunes
Dr Tugba Gunes obtained her B.Sc and M.Sc degrees in the field of statistics and obtained her PhD from the department of Real Estate Development and Management at the Ankara University applying real estate finance studies and automated valuation models. She studied for one year of her PhD as a visiting scholar at the Land Economy department of the University of Cambridge. She is a licensed property appraiser and has been working as a statistician with senior expertise in mass valuation at the Land Registry and Cadastre Agency in Türkiye. She also worked for property valuation and taxation projects supported by the World Bank. Her research interests are property valuation, real estate economics and finance, and machine learning applications.