The (Marginal) Value of a Search Ad: An Online Causal Framework for Repeated Second-price Auctions

TL;DR

This paper introduces a causal framework for bidding in second-price auctions, modeling ad value as a treatment effect and developing algorithms with optimal regret, leveraging the auction's payment rule for improved learning.

Contribution

It proposes a novel causal modeling approach for ad valuation in second-price auctions and develops rate-optimal algorithms that utilize auction payment information.

Findings

Algorithms achieve rate-optimal regret under multiple feedback models.

Leveraging second-price payment information improves learning efficiency.

Model captures the true marginal value of ads beyond immediate revenue.

Abstract

Existing auto-bidding algorithms in digital advertising often treat the value of an ad opportunity as the revenue obtained when an ad is shown and/or clicked, and bid accordingly. This can lead to wasteful spending because the true value is the marginal gain from paid exposure: even without winning a sponsored slot, an advertiser may still earn revenue via an organic search result (e.g., on Google or Amazon). Motivated by recent work, we model ad value as a treatment effect--the outcome difference between winning and losing the auction--and study online learning for bidding in second-price (Vickrey) auctions under this causal perspective. We develop algorithms that attain rate-optimal regret under several feedback models. A key ingredient exploits the information revealed by the second-price payment rule, which strictly improves regret relative to analogous learning problems in first-price auctions.