Bid Shading in The Brave New World of First-Price Auctions
This addresses the need for advertisers and demand platforms to adapt to volatile first-price auction environments, though it appears incremental as it builds on known bid shading techniques.
The study tackled the problem of preventing overpaying in first-price online ad auctions by proposing a machine learning approach for optimal bid shading, demonstrating its superiority and robustness across performance metrics in offline and online evaluations on a major demand-side platform.
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.