We construct a neural network algorithm that generates price predictions for art at auction, relying on both visual and non-visual object characteristics. We find that higher automated valuations relative to auction house pre-sale estimates are associated with substantially higher...

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...

This paper investigates the price determinants and investment performance of art. We apply a hedonic regression analysis to a new data set of more than one million auction transactions of paintings and works on paper. Based on the resulting price index, we conclude that art has appreciated in...

Aggregate art price patterns mask a lot of underlying variation — both in the time series and in the cross-section. The authors argue that, to increase our understanding of the market for aesthetics, it is helpful to take a micro perspective on the formation of art prices, and acknowledge that...

This paper presents a model of trading in unique durable assets that provide idiosyncratic payoffs, such as art, luxury real estate, and firm subsidiaries. Agents make purchase and sale decisions in an auction market based on their private use value of the asset and on the expected resale...

We construct a neural network algorithm that generates price predictions for art at auction, relying on both visual and non-visual object characteristics. We find that higher automated valuations relative to auction house pre-sale estimates are associated with substantially higher...

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...