用超长用户行为序列提升推荐点击率，支持实时预测下一步动作。
TransAct V2: Lifelong User Action Sequence Modeling on Pinterest Recommendation
- 使用极长用户序列建模长期行为偏好
- 引入下一步动作损失函数，提升行为预测准确率
- 专为大规模序列模型设计低延迟部署方案
在工业级推荐系统研究中，用户行为序列建模已成为点击率（CTR）预测的热点。然而，现有大规模CTR模型通常仅依赖短序列，难以捕捉长期行为；同时，这些模型普遍缺乏在点对点排序框架内集成动作预测任务的能力，限制了其预测性能；此外，很少有工作关注大规模序列模型高效服务的基础设施挑战。本文提出TransAct V2，作为Pinterest首页推荐系统的生产级模型，包含三项关键创新：(1) 利用极长用户序列以提升CTR预测效果；(2) 引入下一动作损失函数，增强用户行为预测能力；(3) 采用可扩展、低延迟的部署方案，应对延长行为序列带来的计算压力。
原文摘要 · Abstract (English)
Modeling user action sequences has become a popular focus in industrial recommendation system research, particularly for Click-Through Rate (CTR) prediction tasks. However, industry-scale CTR models often rely on short user sequences, limiting their ability to capture long-term behavior. Additionally, these models typically lack an integrated action-prediction task within a point-wise ranking framework, reducing their predictive power. They also rarely address the infrastructure challenges involved in efficiently serving large-scale sequential models. In this paper, we introduce TransAct V2, a production model for Pinterest's Homefeed ranking system, featuring three key innovations: (1) leveraging very long user sequences to improve CTR predictions, (2) integrating a Next Action Loss function for enhanced user action forecasting, and (3) employing scalable, low-latency deployment solutions tailored to handle the computational demands of extended user action sequences.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。