Generative recommendation improves advertising revenue and efficiency
Towards Reliable, Scalable, and Value-Aligned Generative Recommendation for Large-Scale Advertising
Information RetrievalMachine Learning
Summary
Online advertising platforms need to show personalized ads that users are likely to engage with while keeping the process fast. The authors improve an existing system that generates ad identifiers by making it more reliable, scaling its capacity efficiently, and better aligning recommendations with business value. Their improved system, tested on a large platform, increased revenue by about 3% while meeting strict speed and throughput requirements. This work helps balance the trade-offs between effectiveness and efficiency in ad recommendation.
What this means in practice
- •For online advertising engineers: Enhance ad recommendation systems to increase revenue while maintaining strict latency and throughput limits using reliable and value-aligned generative models.$Commercial implications: Enables improved ad delivery platforms that increase revenue and meet performance requirements for large-scale digital advertisers.
- •For e-commerce platform developers: Implement generative recommendation models to personalize product retrieval better while optimizing the trade-off between recommendation quality and serving efficiency.
Authors
Yatong Xiao, Yibo Sheng, Lixiang Wang, Mingjie Sun, Yunhao Sha, Pengfei Zhang, Shengyu Wang, Peng Wang, Wenjin Wu, Peng Jiang
Abstract
Generative recommendation (GR) reformulates item retrieval as autoregressive generation of discrete semantic identifiers (SIDs), offering a unified paradigm for personalized recommendation. GR4AD, as an industrial generative recommendation framework, has greatly improved advertising revenue while enabling efficient real-time serving in Kuaishou.However, continued deployment has exposed three limitations: deterministic SID assignment remains sensitive to semantic boundaries; conventional backbone scaling provides diminishing revenue gains under strict serving constraints; and sequence-level value optimization provides limited credit assignment to intermediate SID decisions, causing likelihood-based beam search to prematurely prune potentially high-value candidates. We present GR4AD-X, which addresses these limitations through reliable SID construction, serving-efficient capacity scaling, and unified value alignment. Specifically, GR4AD-X improves SID reliability through Multi-Path assignment. It expands model capacity along multiple complementary dimensions rather than relying solely on wider or deeper backbones, achieving a better effectiveness-efficiency trade-off under strict serving constraints. Finally, Unified Value-Guided Generation and Discrimination (UniVGD) aligns generation with commercial value through prefix-level reward optimization, value-guided beam pruning, and discriminative reranking within a unified model. Large-scale online A/B tests on the Kuaishou advertising platform demonstrate that GR4AD-X achieves a cumulative revenue improvement of 3.07% over the deployed GR4AD baseline while satisfying strict latency and throughput constraints.