Google Research

Testing Dynamic Incentive Compatibility in Display Ad Auctions

Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (2019), pp. 1616-1624


The question of transparency has become a key point of contention between buyers and sellers of display advertising space: ads are allocated via complex, black-box auction systems whose mechanics can be difficult to model let alone optimize against. Motivated by this concern, this paper takes the perspective of a single advertiser and develops statistical tests to confirm whether an underlying auction mechanism is dynamically incentive compatible (IC), so that truthful bidding in each individual auction and across time is an optimal strategy. The most general notion of dynamic-IC presumes that the seller knows how buyers discount future surplus, which is questionable in practice. We characterize dynamic mechanisms that are dynamic-IC for all possible discounting factors according to two intuitive conditions: the mechanism should be IC at each stage in the usual sense, and expected present utility (under truthful bidding) should be independent of past bids. The conditions motivate two separate experiments based on bid perturbations that can be run simultaneously on the same impression traffic. We provide a novel statistical test of stage-IC along with a test for utility-independence that can detect lags in how the seller uses past bid information. We evaluate our tests on display ad data from a major ad exchange and show how they can accurately uncover evidence of first- or second-price auctions coupled with dynamic reserve prices, among other types of dynamic mechanisms.

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work