English(EN) Jointly Optimizing Debiased CTR and Uplift for Coupons Marketing: A Unified Causal Framework

新框架解决优惠券营销中的广告偏见

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-02 04:00

研究人员开发了一个名为UniMVT的新框架，用于解决在线广告中的混淆偏见，特别是在优惠券营销方面。该模型将用户偏好与优惠券等干预措施的效果分离开来，从而能够更准确地预测基础点击率（CTR）并估算提升效果。UniMVT能够处理多值处理，并通过真实的A/B测试在预测准确性、校准和业务指标方面显示出显著的改进。 AI

影响通过减轻点击率预测中的偏见，提高了广告定位和优惠券分发的准确性。

排序理由该集群包含一篇详细介绍新框架和方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

UniMVT

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Siyun Yang, Shixiao Yang, Jian Wang, Di Fan, Kehe Cai, Haoyan Fu, Jiaming Zhang, Wenjin Wu, Peng Jiang · 2026-06-02 04:00

Jointly Optimizing Debiased CTR and Uplift for Coupons Marketing: A Unified Causal Framework

arXiv:2602.12972v2 Announce Type: replace-cross Abstract: In online advertising, marketing interventions such as coupons introduce significant confounding bias into Click-Through Rate (CTR) prediction. Observed clicks reflect a mixture of users' intrinsic preferences and the upli…

报道来源 [1]

Jointly Optimizing Debiased CTR and Uplift for Coupons Marketing: A Unified Causal Framework

相关话题