Dynamic Price Forecasting in Simultaneous Online Art Auctions

The global art market has undergone a huge transition in the last decade leading to the creation of new art hedge funds, art mutual funds, and art online auction sites. The increasing interest in the overall art market has also helped popularize emerging art markets such as Indian contemporary art. In this paper we focus on simultaneous online auctions (SOA) for Indian contemporary art. SOAs sell high-value items in auctions that take place simultaneously and are different from popular individual auctions (e.g. eBay) in multiple ways and in particular in that they induce high levels of competition both within and between auctions. The SOA art marketplace has the promise of extremely high profits but also the risk of high losses if not monitored carefully. Forecasting price during an ongoing SOA is therefore important to auction house managers, who can make real-time decisions and intervene while an auction is in progress. We present a novel dynamic forecasting approach for predicting price in ongoing simultaneous online art auctions. Our model forecasts the price from the time of prediction until auction close and updates its prediction in real-time as the auction progresses based on newly arriving information and price dynamics. We find high predictive accuracy of the dynamic model for a data set of contemporary Indian art SOAs and compare its performance to more traditional approaches. We then investigate the source of the predictive power of price dynamics and find that dynamics capture bidder competition within and across auctions. The importance of this finding is both conceptual and practical: price dynamics are simple to compute at high accuracy, as they require information only from the focal auction and are therefore a parsimonious representation of different forms of within-auction and between-auction competition.