Generative Bid Shading in Real-Time Bidding Advertising

TL;DR

This paper introduces Generative Bid Shading (GBS), a novel approach for real-time bidding that models complex bid landscapes with an autoregressive generative model and aligns rewards to optimize surplus, validated through extensive experiments and deployment.

Contribution

The paper presents GBS, a new generative bid shading method that overcomes limitations of existing models by capturing complex dependencies and optimizing long-term surplus.

Findings

GBS outperforms traditional methods in offline and online tests.

GBS is deployed on Meituan DSP, handling billions of requests daily.

Experimental results show improved surplus and bidding efficiency.

Abstract

Bid shading plays a crucial role in Real-Time Bidding (RTB) by adaptively adjusting the bid to avoid advertisers overspending. Existing mainstream two-stage methods, which first model bid landscapes and then optimize surplus using operations research techniques, are constrained by unimodal assumptions that fail to adapt for non-convex surplus curves and are vulnerable to cascading errors in sequential workflows. Additionally, existing discretization models of continuous values ignore the dependence between discrete intervals, reducing the model's error correction ability, while sample selection bias in bidding scenarios presents further challenges for prediction. To address these issues, this paper introduces Generative Bid Shading (GBS), which comprises two primary components: 1) an end-to-end generative model that utilizes an autoregressive approach to generate shading ratios by stepwise residuals, capturing complex value dependencies without relying on predefined priors; and 2) a reward preference alignment system, which incorporates a channel-aware hierarchical dynamic network (CHNet) as the reward model to extract fine-grained features, along with modules for surplus optimization and exploration utility reward alignment, ultimately optimizing both short-term and long-term surplus using group relative policy optimization (GRPO). Extensive experiments on both offline and online A/B tests validate GBS's effectiveness. Moreover, GBS has been deployed on the Meituan DSP platform, serving billions of bid requests daily.