Revenue Optimization with Approximate Bid Predictions

TL;DR

This paper presents a method to optimize reserve prices in advertising auctions by reducing the problem to standard prediction tasks, establishing a formal link between prediction accuracy and revenue outcomes.

Contribution

It introduces a novel reduction of reserve price optimization to squared loss prediction, providing theoretical bounds on revenue based on predictor quality.

Findings

Bounded the revenue gap using prediction loss

First formal relation between bid prediction accuracy and revenue

Applicable to heterogeneous ad auction settings

Abstract

In the context of advertising auctions, finding good reserve prices is a notoriously challenging learning problem. This is due to the heterogeneity of ad opportunity types and the non-convexity of the objective function. In this work, we show how to reduce reserve price optimization to the standard setting of prediction under squared loss, a well understood problem in the learning community. We further bound the gap between the expected bid and revenue in terms of the average loss of the predictor. This is the first result that formally relates the revenue gained to the quality of a standard machine learned model.