用反事实估计优化商品页信号推荐，提升高单价商品转化率
Stageboost: Recommending Signals Based on Counterfactual Estimation
- 两阶段XGBoost模型根据反事实预测选择最优信号展示
- 线上实验显示整体商品成交额提升0.08%，配件类提升0.58%
- 适合电商推荐系统、个性化信号优化场景
信号是显示在eBay商品详情页（VI页面）上的短文本或视觉片段，为用户查看的商品提供额外上下文信息，旨在促进智能购买并激励用户互动。本文提出一种基于两阶段XGBoost的模型，用于最优地填充VI页面的信号内容。该方法在线上实验中实现了整体商品成交额（GMB）0.08%的提升，以及配件类商品成交额0.58%的增长，主要得益于高单价商品转化率的提高。
原文摘要 · Abstract (English)
Signals are short textual or visual snippets displayed on the eBay View-Item (VI) page, providing additional, contextual information for users about the viewed item. The aim of displaying these signals is to facilitate intelligent purchase and to incentivize engagement. In this paper, we present a 2 stage xgboost based model that optimally populates the VI page with signals. This approach has shown a 0.08% lift in overall GMB (Gross Merchandise Bought) and 0.58% increase in Parts and Accessories GMB, primarily due to increase in conversion of high average price items in online experimentation.
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。