分离用户点击习惯与真实兴趣，提升推荐精准度。
OrDA: Orthogonal Disentanglement of Access Habits Framework for Homepage Marketing Block Recommendations
- 双塔结构+门控路由，动态分流兴趣与习惯特征
- 正交约束使兴趣与习惯表征完全垂直，消除干扰
- 因果干预排序，仅按纯兴趣打分，适合电商首页推荐
主页营销模块的点击行为受内容兴趣和访问习惯双重驱动。但习惯性点击常导致营销位出现伪正例，位置优势掩盖内容质量不足，造成推荐系统偏差。本文提出正交解耦访问习惯框架（OrDA），通过双塔结构配合门控分配层自适应路由特征，以正交正则化强制兴趣与习惯潜空间几何垂直，实现严格分离。推理时采用因果干预（do-计算）仅基于净化后的兴趣得分排序。大规模数据集实证表明，OrDA有效消除访问习惯偏差，在预测准确率上优于现有方法。线上AB测试显示，芝麻首页营销模块点击率提升5.64%，在芝麻租凭定价推荐场景中验证有效。
原文摘要 · Abstract (English)
Clicks on homepage marketing blocks are driven by a dual-mechanism of content interest and access habits. However, habitual clicks often create Pseudo-Positives in marketing slots, where position advantage masks mediocre content quality, leading to biased recommendation ecosystems. We propose a framework called Orthogonal Disentanglement of Access habits (OrDA) to purify interest signals. OrDA utilizes a dual-tower structure with a gated allocation layer to adaptively route features and minimize interference. To ensure rigorous separation, we employ orthogonal regularization to constrain the latent interest and habit manifolds to be geometrically perpendicular. OrDA performs causal intervention (do-calculus) during inference to rank items solely by purified interest scores. Empirical online evaluations on large-scale datasets demonstrate that OrDA effectively eliminates access-habit bias, outperforming state-of-the-art methods in predictive accuracy. Online AB test 5.64% shows user click-through rates (UCTR) improvement on the Zhima homepage marketing block, Zhima rent-floor recommendation.
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。