Auto-bidding under Return-on-Spend Constraints with Uncertainty Quantification
It addresses a key challenge in online advertising for platforms and advertisers by enhancing auto-bidding systems with uncertainty handling, though it builds incrementally on existing methods.
This paper tackles the problem of auto-bidding in advertising under Return-on-Spend constraints when ad impression values are unknown, proposing a method that uses conformal prediction for uncertainty quantification and showing improved performance with theoretical guarantees on simulated and real-world datasets.
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.