Optimal Boost Design for Auto-bidding Mechanism with Publisher Quality Constraints

TL;DR

This paper proposes a novel method for optimizing boost factors in online ad bidding that balances platform efficiency and publisher quality, demonstrating significant welfare gains in real-world data.

Contribution

It introduces a three-party auction framework with a unified welfare metric and a new q-Boost algorithm for optimal boost computation, addressing quality concerns in ad auctions.

Findings

Achieves 2%-6% welfare improvement over traditional methods

Derives theoretical efficiency lower bounds for boost factors

Validates effectiveness on Alibaba's AuctionNet dataset

Abstract

Online bidding serves as a fundamental information system in mobile ecosystems, facilitating real-time ad allocation across billions of devices while optimizing both platform performance and user experience through data-driven decision making. Improving ad allocation efficiency is a long-standing research problem, as it directly enhances the economic outcomes for all participants in advertising platforms. This paper investigates the design of optimal boost factors in online bidding while incorporating quality value (the impact of displayed ads on publishers' long-term benefits). To address the divergent interests on quality, we establish a three-party auction framework with a unified welfare metric of advertiser and publisher. Within this framework, we derive the theoretical efficiency lower bound for C-competitive boost in second-price single-slot auctions, then design a novel quality-involved Boosting (q-Boost) algorithm for computing the optimal boost factor. Experimental validation on Alibaba's public dataset (AuctionNet) demonstrates 2%-6% welfare improvements over conventional approaches, proving our method's effectiveness in real-world settings.