Auto-bidding under Return-on-Spend Constraints with Uncertainty Quantification

2025-09-19

AI Summary

This paper addresses the practical challenges in automated advertising bidding—namely, unknown true conversion values and strict budget and return-on-spend (RoS) constraints. We propose a novel framework integrating machine learning prediction with conformal prediction. Our key contribution is the first application of conformal prediction to automated bidding, enabling a distribution-free, context-aware value estimator that constructs statistically rigorous prediction intervals from historical bid contexts without requiring i.i.d. assumptions. We further design an interval-driven, risk-aware bidding policy that explicitly accounts for uncertainty. Crucially, the method operates without ground-truth value labels, yet significantly reduces RoS constraint violations while improving revenue and constraint satisfaction rates. Extensive experiments on both synthetic and real-world industrial datasets demonstrate its computational efficiency, system compatibility, and robust performance. The approach provides a theoretically sound, uncertainty-aware, and production-ready solution for large-scale advertising platforms.

Technology Category

• Machine Learning: Online Learning & Bandits
• Game Theory and Economic Paradigms: Adversarial Learning
• Reasoning under Uncertainty: Sequential Decision Making

Application Category

• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Advertising auctions, pricing, markets, and exchanges

Abstract

Auto-bidding systems are widely used in advertising to automatically determine bid values under constraints such as total budget and Return-on-Spend (RoS) targets. Existing works often assume that the value of an ad impression, such as the conversion rate, is known. This paper considers the more realistic scenario where the true value is unknown. We propose a novel method that uses conformal prediction to quantify the uncertainty of these values based on machine learning methods trained on historical bidding data with contextual features, without assuming the data are i.i.d. This approach is compatible with current industry systems that use machine learning to predict values. Building on prediction intervals, we introduce an adjusted value estimator derived from machine learning predictions, and show that it provides performance guarantees without requiring knowledge of the true value. We apply this method to enhance existing auto-bidding algorithms with budget and RoS constraints, and establish theoretical guarantees for achieving high reward while keeping RoS violations low. Empirical results on both simulated and real-world industrial datasets demonstrate that our approach improves performance while maintaining computational efficiency.

Problem

• Addresses auto-bidding with uncertain ad impression values
• Quantifies uncertainty in conversion rates using conformal prediction
• Ensures performance guarantees under budget and RoS constraints

Innovation

• Uses conformal prediction for uncertainty quantification
• Introduces adjusted value estimator from ML predictions
• Enhances auto-bidding algorithms with theoretical guarantees