Learning Theory and Algorithms for Revenue Management in Sponsored Search

TL;DR

This paper introduces new loss functions and ranking strategies for sponsored search ads that directly optimize revenue metrics, utilizing deep learning models and real-world data to outperform existing methods.

Contribution

It proposes revenue-based loss functions and ranking models, including deep learning approaches, to better align ad ranking with revenue optimization in sponsored search.

Findings

Proposed loss functions improve revenue metrics over CTR-based models.

Explicit and implicit ranking models outperform state-of-the-art methods.

Deep models effectively optimize revenue in real-world datasets.

Abstract

Online advertisement is the main source of revenue for Internet business. Advertisers are typically ranked according to a score that takes into account their bids and potential click-through rates(eCTR). Generally, the likelihood that a user clicks on an ad is often modeled by optimizing for the click through rates rather than the performance of the auction in which the click through rates will be used. This paper attempts to eliminate this dis-connection by proposing loss functions for click modeling that are based on final auction performance.In this paper, we address two feasible metrics (AUC^R and SAUC) to evaluate the on-line RPM (revenue per mille) directly rather than the CTR. And then, we design an explicit ranking function by incorporating the calibration fac-tor and price-squashed factor to maximize the revenue. Given the power of deep networks, we also explore an implicit optimal ranking function with deep model. Lastly, various experiments with two real world datasets are presented. In particular, our proposed methods perform better than the state-of-the-art methods with regard to the revenue of the platform.