Search

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.

We present an infinite-horizon model of endogenous trading in the art auction market. Agents make purchase and sale decisions based on the relative magnitude of their private use value in each period. Our model generates endogenous cross-sectional and time-series patterns in investment outcomes. Average returns and buy-in probabilities are negatively correlated with the time between purchase and resale (attempt). Idiosyncratic risk does not converge to zero as the holding period shrinks. Prices and auction volume increase during expansions. Our model finds empirical support in auction data and has implications for selection biases in observed prices and transaction-based price indexes.