Authors: Yinqiu Huang, Shuli Wang, Min Gao, Xue Wei, Changhao Li, Chuan Luo, Yinhua Zhu, Xiong Xiao, Yi Luo

Published on: February 04, 2024

Impact Score: 8.15

Arxiv code: Arxiv:2402.03379

Summary

• What is new: Introduction of the Entire Chain UPlift method with context-enhanced learning (ECUP) to address the chain-bias and treatment-unadaptive problems in uplift modeling.
• Why this is important: Existing uplift modeling techniques in online marketing fail to consider the sequential user behavior chain and the nuanced effects of treatments, leading to potential bias in marketing decisions.
• What the research proposes: The ECUP approach integrates an Entire Chain-Enhanced Network for estimating ITE across the user behavior chain and a Treatment-Enhanced Network for fine-grained treatment modeling.
• Results: ECUP demonstrated improved performance in experiments on public and industrial datasets and has been successfully deployed on the Meituan food delivery platform.

Technical Details

Technological frameworks used: ECUP

Models used: Entire Chain-Enhanced Network, Treatment-Enhanced Network

Data used: Public and industrial datasets, Meituan food delivery platform data

Potential Impact

Online marketing, e-commerce platforms, specifically food delivery platforms like Meituan

Want to implement this idea in a business?

We have generated a startup concept here: Chainfluence.