Machine Learning, Human Experts, and the Valuation of Real Assets

35 Pages Posted: 20 Mar 2019 Last revised: 28 Jan 2020

See all articles by Mathieu Aubry

Mathieu Aubry

Ecole Nationale des Ponts et Chaussées (ENPC)

Roman Kräussl

Luxembourg School of Finance; Hoover Institution, Stanford University

Gustavo Manso

University of California, Berkeley - Haas School of Business

Christophe Spaenjers

HEC Paris - Finance Department

Date Written: June 23, 2019

Abstract

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.

Keywords: asset valuation, auctions, experts, big data, machine learning, computer vision, art

JEL Classification: C50, D44, G12, Z11

Suggested Citation

Aubry, Mathieu and Kraeussl, Roman and Manso, Gustavo and Spaenjers, Christophe, Machine Learning, Human Experts, and the Valuation of Real Assets (June 23, 2019). HEC Paris Research Paper No. FIN-2019-1332; 10th Miami Behavioral Finance Conference. Available at SSRN: https://ssrn.com/abstract=3347175 or http://dx.doi.org/10.2139/ssrn.3347175

Mathieu Aubry

Ecole Nationale des Ponts et Chaussées (ENPC) ( email )

28, rue des Saints-Peres
75343 Paris Cedex 07
France

HOME PAGE: http://imagine.enpc.fr/~aubrym/

Roman Kraeussl

Luxembourg School of Finance ( email )

4, rue Albert Borschette
Luxembourg, 1246
Luxembourg
+3524666445442 (Phone)

HOME PAGE: http://www.art-finance.com

Hoover Institution, Stanford University ( email )

Stanford, CA 94305
United States

Gustavo Manso

University of California, Berkeley - Haas School of Business ( email )

545 Student Services Building, #1900
2220 Piedmont Avenue
Berkeley, CA 94720
United States

Christophe Spaenjers (Contact Author)

HEC Paris - Finance Department ( email )

1 rue de la Liberation
Jouy-en-Josas Cedex, 78351
France

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
318
Abstract Views
1,813
rank
98,487
PlumX Metrics