解决广告排序中多目标优化的偏差与量纲不一致问题
CaliCausalRank: Calibrated Multi-Objective Ad Ranking with Robust Counterfactual Utility Optimization
- 将分数校准作为训练目标，统一不同流量段的评分尺度
- 在Criteo和Avazu数据集上提升3.2%收益，校准误差降低31.6%
- 适合大规模广告系统优化，尤其关注公平性与跨场景一致性
广告排序系统需同时优化点击率（CTR）、转化率（CVR）、收入及用户体验指标。但实际系统面临两大挑战：不同流量段间得分量纲不一致导致阈值难以迁移，点击日志中的位置偏差引发离线与在线指标差异。本文提出CaliCausalRank，一个统一框架，融合训练期量纲校准、基于约束的多目标优化与鲁棒反事实效用估计。该方法将分数校准视为首要训练目标，采用拉格朗日松弛保证约束满足，并使用方差缩减的反事实估计器实现可靠离线评估。在Criteo和Avazu数据集上的实验表明，相比最佳基线PairRank，CaliCausalRank实现1.1%相对AUC提升，校准误差减少31.6%，效用增长3.2%，且在不同流量段保持性能一致。
原文摘要 · Abstract (English)
Ad ranking systems must simultaneously optimize multiple objectives including click-through rate (CTR), conversion rate (CVR), revenue, and user experience metrics. However, production systems face critical challenges: score scale inconsistency across traffic segments undermines threshold transferability, and position bias in click logs causes offline-online metric discrepancies. We propose CaliCausalRank, a unified framework that integrates training-time scale calibration, constraint-based multi-objective optimization, and robust counterfactual utility estimation. Our approach treats score calibration as a first-class training objective rather than post-hoc processing, employs Lagrangian relaxation for constraint satisfaction, and utilizes variance-reduced counterfactual estimators for reliable offline evaluation. Experiments on the Criteo and Avazu datasets demonstrate that CaliCausalRank achieves 1.1% relative AUC improvement, 31.6% calibration error reduction, and 3.2% utility gain compared to the best baseline (PairRank) while maintaining consistent performance across different traffic segments.
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。