Artificial Intelligence and Auction Design

31 Pages Posted: 16 Feb 2022

See all articles by Martino Banchio

Martino Banchio

Stanford Graduate School of Business

Andrzej Skrzypacz

Stanford University - Stanford Graduate School of Business

Date Written: February 12, 2022

Abstract

Motivated by online advertising auctions, we study auction design in repeated auctions played by simple Artificial Intelligence algorithms (Q-learning). We find that first-price auctions with no additional feedback lead to tacit-collusive outcomes (bids lower than values), while second-price auctions do not. We show that the difference is driven by the incentive in first-price auctions to outbid opponents by just one bid increment. This facilitates re-coordination on low bids after a phase of experimentation. We also show that providing information about the lowest bid to win, as introduced by Google at the time of the switch to first-price auctions, increases the competitiveness of auctions.

Keywords: Auction Design, Q-learning, Algorithmic Bidding

Suggested Citation

Banchio, Martino and Skrzypacz, Andrzej, Artificial Intelligence and Auction Design (February 12, 2022). Available at SSRN: https://ssrn.com/abstract=4033000 or http://dx.doi.org/10.2139/ssrn.4033000

Martino Banchio

Stanford Graduate School of Business ( email )

655 Knight Way
Stanford, 94305
United States

HOME PAGE: http://https://sites.google.com/view/martinobanchio

Andrzej Skrzypacz (Contact Author)

Stanford University - Stanford Graduate School of Business ( email )

655 Knight Way
Stanford, CA 94305-5015
United States
650-736-0987 (Phone)
650-725-9932 (Fax)

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
111
Abstract Views
325
rank
343,402
PlumX Metrics