探索行为特征时间窗口对电商搜索排序的影响
Long or Short or Both? An Exploration on Lookback Time Windows of Behavioral Features in Product Search Ranking
- 融合长短时间窗口的行为特征，提升排序效果
- 查询级垂直信号显著增强特征聚合能力
- 适用于电商平台搜索排序优化场景
用户购物行为特征是电子商务搜索排序模型的核心。本文研究在历史数据中以（查询，商品）为单位聚合行为特征时，不同回顾时间窗口（长/短）的影响。通过分析长短窗口的优劣，提出一种整合多时间窗口行为特征的新方法。特别强调在排序模型中使用查询级垂直信号的重要性，以有效聚合来自不同行为特征的信息。该方法在沃尔玛官网真实搜索流量上得到验证，表现出良好效果。
原文摘要 · Abstract (English)
Customer shopping behavioral features are core to product search ranking models in eCommerce. In this paper, we investigate the effect of lookback time windows when aggregating these features at the (query, product) level over history. By studying the pros and cons of using long and short time windows, we propose a novel approach to integrating these historical behavioral features of different time windows. In particular, we address the criticality of using query-level vertical signals in ranking models to effectively aggregate all information from different behavioral features. Anecdotal evidence for the proposed approach is also provided using live product search traffic on Walmart.com.
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。