Feedback Control for Small Budget Pacing
This provides a scalable and reliable solution for budget pacing, particularly benefiting small-budget advertising campaigns, though it is incremental as it builds on existing control theory and advertising systems.
The paper tackled the problem of unstable and inefficient budget pacing in online advertising by proposing a principled controller combining bucketized hysteresis with proportional feedback, resulting in a 13% reduction in pacing error and 54% reduction in volatility compared to baseline methods.
Budget pacing is critical in online advertising to align spend with campaign goals under dynamic auctions. Existing pacing methods often rely on ad-hoc parameter tuning, which can be unstable and inefficient. We propose a principled controller that combines bucketized hysteresis with proportional feedback to provide stable and adaptive spend control. Our method provides a framework and analysis for parameter selection that enables accurate tracking of desired spend rates across campaigns. Experiments in real-world auctions demonstrate significant improvements in pacing accuracy and delivery consistency, reducing pacing error by 13% and $λ$-volatility by 54% compared to baseline method. By bridging control theory with advertising systems, our approach offers a scalable and reliable solution for budget pacing, with particular benefits for small-budget campaigns.