Bid Shading in The Brave New World of First-Price Auctions

TL;DR

This paper introduces a machine learning method for optimal bid shading in first-price online ad auctions, addressing the challenge of overpaying and adapting to the evolving auction environment, with demonstrated superior performance.

Contribution

It proposes a novel machine learning approach for modeling optimal bid shading in first-price auctions, improving over existing methods and enhancing auction efficiency.

Findings

The approach outperforms existing bid shading methods in offline evaluations.

It demonstrates robustness and superior performance in online deployment.

The method effectively adapts to the volatile auction environment.

Abstract

Online auctions play a central role in online advertising, and are one of the main reasons for the industry's scalability and growth. With great changes in how auctions are being organized, such as changing the second- to first-price auction type, advertisers and demand platforms are compelled to adapt to a new volatile environment. Bid shading is a known technique for preventing overpaying in auction systems that can help maintain the strategy equilibrium in first-price auctions, tackling one of its greatest drawbacks. In this study, we propose a machine learning approach of modeling optimal bid shading for non-censored online first-price ad auctions. We clearly motivate the approach and extensively evaluate it in both offline and online settings on a major demand side platform. The results demonstrate the superiority and robustness of the new approach as compared to the existing approaches across a range of performance metrics.