The Predictability of House Prices: “Human Against Machine”


Start Page / End Page


Issue Number



Kristoffer B. Birkeland, Allan D. D’Silva, Roland Füss, Are Oust

139 / 183




International Real Estate Review



We develop an automated valuation model (AVM) for the residential real estate market by leveraging stacked generalization and a comparable market analysis. Specifically, we combine four novel ensemble learning methods with a repeat sales method and tailor the data selection for each value estimate. We calibrate and evaluate the model for the residential real estate market in Oslo by producing out-of-sample estimates for the value of 1,979 dwellings sold in the first quarter of 2018. Our novel approach of using stacked generalization achieves a median absolute percentage error of 5.4%, and more than 96% of the dwellings are estimated within 20% of their actual sales price. A comparison of the valuation accuracy of our AVM to that of the local estate agents in Oslo generally demonstrates its viability as a valuation tool. However, in stable market phases, the machine falls short of human capability.


Download Entire Article



AVMs, Housing Market, Machine Learning, Repeat Sales Approach, XGBoost.