Selling to Non-linear Agents: A Demand-Based Auction

Abstract

Auctions allocate scarce goods, from car licenses to online advertising, to buyers whose utilities are often not linear in money, as with budgets or risk aversion. We ask how a seller should sell to such buyers and what learning their preferences is worth. We propose demand-based auctions, which elicit demand curves and are dominant-strategy incentive compatible for any non-linear utilities. The revenue-maximizing one takes familiar second-price forms and is max-min optimal when the seller observes only demand curves. Under standard assumptions, learning risk attitudes beyond demand curves adds relatively little revenue, as does learning budgets unless they correlate with values.