Skip to content
Book Open access

Decision-Focused Learning for Bidding Optimization in Online Advertising

Nov 2026 · ACM Interational Symposium on Mobile Ad Hoc Networking and Computing · pp. 341-350 · 0 citations · 17 references
Computer Science

TL;DR

This work proposes the Decision-Focused Bidding (DFB) approach, which retains the predict-then-optimize workflow, but integrates the downstream objective into the training of the prediction model, and proposes Enhanced DFB (EDFB), which jointly optimizes both objectives to achieve robust generalization in real-world bidding environments.

Abstract

In large-scale networked systems such as online marketplaces and advertising exchanges, real-time decision-making under dynamic environments is a fundamental challenge. A widely adopted paradigm is the predict-then-optimize workflow, where the prediction stage estimates key factors for decisions, and the optimization stage optimizes objectives based on these factors. However, existing prediction models are typically trained only for prediction accuracy, without awareness of the downstream optimization objective, leading to suboptimal results. We investigate this problem in the context of first-price auction bidding, a canonical decision problem in networked platforms. Specifically, we first propose the Decision-Focused Bidding (DFB) approach, which retains the predict-then-optimize workflow, but integrates the downstream objective into the training of the prediction model. To overcome the zero-gradient issue in back-propagation, we develop a smoothed decision mapping that provides usable gradients while preserving clear interpretability in the bidding context. We further show that DFB's decision-learning objective and the classical objective of learning winning probabilities are complementary under non-i.i.d. environments, and accordingly propose Enhanced DFB (EDFB), which jointly optimizes both objectives to achieve robust generalization in real-world bidding environments. Finally, our EDFB approach has been deployed in a production auto-bidding system, where it achieves a 2.3% GMV lift in a 3-day online A/B test over about 100 billion requests.

Read PDF

Similar papers

#machine learning Preprint Oct 2026

Marrying Pricing and Advertising with LLMs

We study a sequential pricing problem in which a seller jointly posts a price and an advertisement generated by a large language model (LLM). The seller aims to maximize revenue under an unknown product demand that depends on both decisions, while observing only whether each offer leads to a purchase. We propose an onl...

Alessandro Barro, Francesco Bacchiocchi, Francesco Emanuele Stradi et al. · 0 citations
Preprint Oct 2026

Reinforcement Learning for Controller Parameters in the Auto-Bidding System at Pinterest

Auto-bidding systems in online advertising must balance competing objectives-maximizing budget delivery while minimizing cost per action-across heterogeneous campaigns under non-stationary market conditions. This trade-off evolves over campaign lifespans: early on, cost optimization dominates when budgets roll over; ne...

Yichu Zhou, Qin-Yi Chen, Fei Feng et al. · 0 citations
Conference

Online Resource Allocation with Predictions

Online decision-makers often obtain predictions on future variables, such as arrivals, demands, inventories, and so on. These predictions can be generated from simple forecasting algorithms for univariate time-series, all the way to state-of-the-art machine learning models that leverage multiple time-series and additio...

Lin An, Andrew A. Li, Benjamin Moseley et al. · 0 citations
Book Open access Nov 2026

TUGB: A Two-stage Uncertainty-aware Generative Auto-Bidding Framework

Generative modeling, particularly Decision Transformers, shows promise in auto-bidding strategies. However, it struggles with limited exploration in static offline datasets, vulnerability to dynamic environmental shifts, and a reliance on heuristic return-to-go (RTG) specifications that may yield suboptimal performance...

Lu-Zhan Yuan, Chao Mi, Xia-Hao Shi et al. · 0 citations
Preprint Nov 2026

DynamAuction: A Reinforcement Learning Environment for Repeated Auctions with Dynamic Value

A buyer who repeatedly participates in auctions for related items often faces a dynamic value problem: what they win today changes what tomorrow's items are worth. Despite the empirical importance of such effects, especially in display advertising, the algorithmic literature on repeated auctions has largely focused on...

Eugénie Patard, Corentin Pla, Benjamin Heymann et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.