Machine learning, human experts, and the valuation of real assets

  • We study the accuracy and usefulness of automated (i.e., machine-generated) valuations for illiquid and heterogeneous real assets. We assemble a database of 1.1 million paintings auctioned between 2008 and 2015. We use a popular machine-learning technique—neural networks—to develop a pricing algorithm based on both non-visual and visual artwork characteristics. Our out-of-sample valuations predict auction prices dramatically better than valuations based on a standard hedonic pricing model. Moreover, they help explaining price levels and sale probabilities even after conditioning on auctioneers’ pre-sale estimates. Machine learning is particularly helpful for assets that are associated with high price uncertainty. It can also correct human experts’ systematic biases in expectations formation—and identify ex ante situations in which such biases are likely to arise.

Download full text files

Export metadata

Author:Mathieu Aubry, Roman KräusslORCiDGND, Gustavo Manso, Christophe Spaenjers
Parent Title (English):Center for Financial Studies (Frankfurt am Main): CFS working paper series ; No. 635
Series (Serial Number):CFS working paper series (635)
Publisher:Center for Financial Studies
Place of publication:Frankfurt, M.
Document Type:Working Paper
Year of Completion:2019
Year of first Publication:2019
Publishing Institution:Universitätsbibliothek Johann Christian Senckenberg
Release Date:2019/11/04
Tag:art; asset valuation; auctions; big data; computer vision; experts; machine learning
Issue:June 23, 2019
Page Number:38
Institutes:Wirtschaftswissenschaften / Wirtschaftswissenschaften
Wissenschaftliche Zentren und koordinierte Programme / Center for Financial Studies (CFS)
Dewey Decimal Classification:3 Sozialwissenschaften / 33 Wirtschaft / 330 Wirtschaft
JEL-Classification:C Mathematical and Quantitative Methods / C5 Econometric Modeling / C50 General
Licence (German):License LogoDeutsches Urheberrecht