CaliCausalRank: 带鲁棒反事实效用优化的校准多目标广告排序
CaliCausalRank: Calibrated Multi-Objective Ad Ranking with Robust Counterfactual Utility Optimization
AI总结：
CaliCausalRank通过整合训练时的尺度校准、约束多目标优化和鲁棒反事实效用估计，提升了广告排序的多目标优化性能。
摘要：
广告排序系统必须同时优化多个目标，包括点击通过率（CTR）、转化率（CVR）、收益和用户体验指标。然而，生产系统面临关键挑战：不同流量段的分数尺度不一致会破坏阈值可转移性，而点击日志中的位置偏差会导致离线-在线指标差异。我们提出了CaliCausalRank，一个统一的框架，整合了训练时的尺度校准、基于约束的多目标优化和鲁棒反事实效用估计。我们的方法将分数校准视为首要的训练目标，而不是事后处理，采用拉格朗日松弛法满足约束，并利用方差减少的反事实估计器进行可靠的离线评估。在Criteo和Avazu数据集上的实验表明，CaliCausalRank相比最佳基线（PairRank）实现了1.1%的相对AUC提升，31.6%的校准误差降低，以及3.2%的效用提升，同时在不同流量段中保持一致的性能。
英文摘要：
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.
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。
