SAGA统一建模跨平台用户行为，提升推荐效果。
SAGA: Structure-Attended Generative Action Embedding Model that encodes Multi-Surface User Action Sequences
- 按字段拆分操作事件，实现细粒度注意力建模。
- 在多个触点上显著提升点击率与转化率。
- 适合需要融合多平台用户行为的推荐系统。
现有序列推荐嵌入模型通常局限于同质行为空间，难以捕捉跨表面的行为信号。本文提出 SAGA，一种生成式动作嵌入模型，将金融服务平台生态中从结账、点对点（P2P）交易、应用内互动、邮件到账户操作等多表面用户交互序列，统一编码为用户表征，用于下游推荐任务。SAGA 的核心是字段级分词方案，将每个动作事件分解为多个字段级标记（如产品、互动、表面），支持字段级注意力与独立训练目标，这是单标记方法无法实现的。通过离线消融实验，我们验证了损失函数设计、分词粒度和训练数据范围的影响。集成 SAGA 嵌入的下游模型在多个下游触点上均表现出最强的点击与转化提升，优于所有消融版本及替代架构。
原文摘要 · Abstract (English)
Prior embedding models for sequential recommendation typically operate within a homogeneous action space, limiting their ability to capture cross-surface behavioral signals spanning distinct behavioral domains. We present SAGA, a generative action embedding model that encodes multi-surface user interaction sequences across a Financial Service organization's ecosystems, from checkout, peer-to-peer (P2P) transactions, in-app engagement, email to account actions, into a unified user representation for downstream recommendation tasks. Central to SAGA is a per-field tokenization schema that decomposes each action event into multiple field-level tokens (e.g. product, interaction, surface), enabling field-level attention and per-field training objectives that fused single-token approaches cannot support. Through an offline ablation study on loss formulation, tokenization granularity and training data scope, we isolate the contribution of each design choice. A downstream model integrated with SAGA-generated user embeddings delivers the strongest overall click and conversion lift across diverse downstream touchpoints, compared to all ablated and alternative architectures.
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。