arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.23530cs.IR
收藏

多通道检索中的大规模电商搜索统一学习排序

Unified Ranking Across Retrieval Channels: A Large-Scale E-Commerce Approach

Data Sciences, Target Corporation(目标公司数据科学部)

Aditya Gaydhani, Guangyue Xu, Dhanush Kamath, Ankit Singh, Alex Fengjie Li

AI总结:

本文提出了一种统一的学习排序模型,用于多通道检索中的大规模电商搜索,通过联合优化点击、加购和购买等指标,提升用户转化率。

摘要:

大规模电商搜索必须从庞大的目录中展示广泛的商品,从畅销品到新潮、季节性商品。现代系统因此依赖多个专门的检索通道来展示商品,每个通道都设计用于满足特定的目标。一个关键挑战是如何在严格的延迟限制下,有效地将这些异构通道的文档合并成一个排序列表,同时优化业务KPI,如用户转化率。基于排名的融合方法,如反向排名融合(RRF)和加权交织,依赖于固定的全局通道权重,并将通道独立处理,未能考虑查询特定的通道效用和跨通道交互。我们观察到,多通道融合可以重新表述为一个查询依赖的学习排序问题,涉及异构候选源。在本文中,我们提出了一种统一的排序模型,该模型学习如何从多个检索通道合并和排序文档。我们将问题表述为一个通道感知的学习排序任务,该任务联合优化点击、加入购物车和购买,同时结合通道特定的目标。我们进一步纳入了最近的用户行为信号,以捕捉短期意图变化,这对于改进多通道排序中的转化至关重要。我们的在线A/B实验显示,所提出的方法优于基于排名的融合方法,导致用户转化率提高了+2.85%。该模型满足生产延迟要求,达到p95延迟低于50毫秒,并已部署在Target.com。

英文摘要:

Large-scale e-commerce search and recommendation systems rely on multiple specialized retrieval channels to surface diverse products, each optimized for a distinct objective. A key challenge is merging candidates from these heterogeneous channels into a single ranked list under strict latency constraints while optimizing business KPIs such as user conversion. Static rank-fusion methods such as Reciprocal Rank Fusion (RRF) and Weighted Interleaving use the same fusion behavior across queries, limiting their ability to adapt to context or model interactions among channel signals. We reformulate multi-channel fusion as a channel-aware learning-to-rank problem and propose a unified ranking model trained on a scalar, funnel-weighted graded-relevance label that combines clicks, add-to-carts, and purchases. The model incorporates channel-specific scores together with recent aggregate query-item behavior to capture near-term population demand. The evaluated channel set combines conventional relevance retrieval with query-conditioned, recommendation-oriented channels emphasizing newness, trending demand, regional relevance, and seasonality. A randomized online experiment shows a 2.85% increase in user conversion over the deployed weighted-interleaving control. The model achieves a p95 reranking-stage latency below 50 ms and has been deployed on Target.com.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑