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

2025-08-12

AI Summary

Existing boost factor design in online advertising auto-bidding neglects long-term publisher quality valuation, leading to suboptimal alignment among advertisers, platforms, and publishers. Method: We propose a quality-aware bidding framework that jointly optimizes the utilities of all three stakeholders. We formulate a tripartite auction model with a unified utility metric and, for the first time, derive a theoretical lower bound on C-competitive boost factors under publisher quality constraints. We further design the q-Boost algorithm to efficiently compute near-optimal boost factors. Contribution/Results: Evaluated on the second-price single-slot auction model using the AuctionNet dataset, our approach improves social welfare by 2–6% over baseline methods—significantly outperforming conventional boost strategies. The framework provides a provably sound, production-ready paradigm for quality-driven ad allocation efficiency.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Online Learning & Bandits
• Multiagent Systems: Mechanism Design

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Online bidding is crucial in mobile ecosystems, enabling real-time ad allocation across billions of devices to optimize performance and user experience. 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.

Problem

• Design optimal boost factors for online bidding with quality constraints
• Balance divergent interests using a three-party auction framework
• Improve welfare in ad allocation via q-Boost algorithm

Innovation

• Three-party auction framework with unified welfare
• Quality-involved Boosting (q-Boost) algorithm
• Theoretical efficiency lower bound for C-competitive boost