Hugging Face Trending Papers

CanniUplift: A Holistic Framework for Mitigating Seller and Incentive Cannibalization in E-commerce Uplift Modeling

Read the original on Hugging Face Trending Papers →

Personalized incentive allocation is vital for e-commerce, where uplift modeling is the standard for estimating Individual Treatment Effects (ITE). However, traditional models often fail in complex multi-seller environments with violations of the Stable Unit Treatment Value Assumption (SUTVA).

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning
6d ago

FunnelCausalNet: Funnel-aware Joint Conversion-Revenue Uplift for Multi-tier Coupon Allocation

arXiv:2608. 11675v1 Announce Type: new Abstract: Coupon campaigns seek to lift both conversion and revenue, but gross merchandise value (GMV) follows a deterministic funnel from conversion to conditional order value and is zero-inflated and heavy-tailed.

By Yu Zhang (AMap Alibaba Group, Beijing, China), Zhihan Wang (AMap Alibaba Group, Beijing, China), Guanlin Chen (AMap Alibaba Group, Beijing, China), Min Jiang (AMap Alibaba Group, Beijing, China), Shuai Li (AMap Alibaba Group, Beijing, China)