Learning and Trust in Auction Markets

Auction theory analyses market designs by assuming all players are fully rational. In this paper we study behavior of bidders in an experimental launch of a new advertising auction platform by Zillow, as Zillow switched from negotiated contracts to using auctions in several geographically isolated markets. A unique feature of this experiment is that the bidders in this market are local real estate agents that bid in the auctions on their own behalf, not using third-party intermediaries to facilitate the bidding. To help bidders, Zillow also provided a recommendation tool that suggested the bid for each bidder. Our main focus in this paper is on the decisions of bidders whether or not to adopt the platform-provided bid recommendation. We observe that a significant proportion of bidders do not use the recommended bid. Using the bid history of the agents we infer their value, and compare the agents’ regret with their actual bidding history with results they would have obtained consistently following the recommendation. We find that for half of the agents not following the recommendation, the increased effort of experimenting with alternate bids results in increased regret, i.e., they get decreased net value out of the system. The proportion of agents not following the recommendation slowly declines as markets mature, but it remains large in most markets that we observe. We argue that the main reason for this phenomenon is the lack of trust that the bidders have in the platform-provided tool. Our work provides an empirical insight into possible design choices for auction-based online advertising platforms. While search advertising platforms (such as Google or Bing) allow bidders to submit bids on their own and there is an established market of third-party intermediaries that help bidders to bid over time, many display advertising platforms (such as Facebook) optimize bids on bidders’ behalf and eliminate the need for the bidders to bid on their own or use intermediaries. Our empirical analysis shows that the latter approach is preferred for markets where bidders are individuals, who don’t have access to third party tools, and who may question the fairness of platform-provided suggestions. ∗Email: [email protected]. Work supported in part by NSF grant CCF-1563714, ONR grant N00014-081-0031, and a Google Research Grant. †Department of Economics, University of Virginia, Monroe Hall, Charlottesville, VA 22904, USA. Email: [email protected]. Work supported in part by NSF grant CCF-1563714 , and a Google Research Grant. ‡Department of Computer Science, Cornell University, Gates Hall, Ithaca, NY 14853, USA, Email: [email protected]. Work supported in part by NSF grant CCF-1563714, ONR grant N00014-08-1-0031, and a Google Research Grant. 1 ar X iv :1 70 3. 10 67 2v 1 [ cs .G T ] 3 0 M ar 2 01 7