Core Data Science
Institutional Affiliation: Facebook
Information about this author at RePEc
NBER Working Papers and Publications
|June 2018||The Simple Empirics of Optimal Online Auctions|
with Bradley Larsen, Kane Sweeney, Caio Waisman: w24698
We study reserve prices computed to maximize the expected profit of the seller based on historical observations of incomplete bid data typically available to the auction designer in online auctions for advertising or e-commerce. This direct approach to computing reserve prices circumvents the need to fully recover distributions of bidder valuations. We derive asymptotic results and also provide a new bound, based on the empirical Rademacher complexity, for the number of historical auction observations needed in order for revenue under the estimated reserve price to approximate revenue under the optimal reserve arbitrarily closely. This simple approach to estimating reserves may be particularly useful for auction design in Big Data settings, where traditional empirical auctions methods may ...
|February 2016||Discounts and Deadlines in Consumer Search|
with Bradley Larsen, Brennan Platt: w22038
We present a new equilibrium search model where consumers initially search among discount opportunities, but are willing to pay more as a deadline approaches, eventually turning to full-price sellers. The model predicts equilibrium price dispersion and rationalizes discount and full-price sellers coexisting without relying on ex-ante heterogeneity. We apply the model to online retail sales via auctions and posted prices, where failed attempts to purchase a good reveal consumers' reservation prices. We find robust evidence supporting the theory, and demonstrate that ignoring buyer deadlines can distort estimates of market welfare, consumer demand, and underlying causes of market shifts.
|September 2014||The Bidder Exclusion Effect|
with Bradley Larsen, Kane Sweeney: w20523
We introduce a simple and robust approach to answering two key questions in empirical auction analysis: discriminating between models of entry and quantifying the revenue gains from improving auction design. The approach builds on Bulow and Klemperer (1996), connecting their theoretical results to empirical work. It applies in a broad range of information settings and auction formats without requiring instruments or estimation of a complex structural model. We demonstrate the approach using US timber and used-car auction data.
Published: Dominic Coey & Bradley Larsen & Kane Sweeney, 2019. "The bidder exclusion effect," The RAND Journal of Economics, vol 50(1), pages 93-120. citation courtesy of
|March 2011||Set-Asides and Subsidies in Auctions|
with Susan Athey, Jonathan Levin: w16851
Set-asides and subsidies are used extensively in government procurement and natural resource sales. We analyze these policies in an empirical model of U.S. Forest Service timber auctions. The model fits the data well both within the sample of unrestricted sales where we estimate the model, and when we predict (out of sample) bidder entry and prices for small business set-asides. Our estimates suggest that restricting entry to small businesses substantially reduces efficiency and revenue, although it does increase small business participation. An alternative policy of subsidizing small bidders would increase revenue and small bidder profit, while eliminating almost all of the efficiency loss of set-asides, and only slightly decreasing the profit of larger firms. We explain these findings by...
Published: Susan Athey & Dominic Coey & Jonathan Levin, 2013. "Set-Asides and Subsidies in Auctions," American Economic Journal: Microeconomics, American Economic Association, vol. 5(1), pages 1-27, February. citation courtesy of