Multi-channel Uplift Policy Learning
Abstract
E-commerce platforms must allocate fixed marketing budgets across multiple channels to maximize business utility. However, standard predict-then-optimize (PTO) paradigms fail in this compositional space due to observational confounding and severe extrapolation. We formulate this challenge as a simplex-constrained uplift decision problem and propose ReAlloc, a fast-slow causal framework. Specifically, an agile Orthogonal Teacher extracts unbiased local gradients from short-term logs, while an Explanation-Guided Student distills them into a structured marginal field over long-term horizons. This design enables support-aware, conservative decisions that capture cross-channel substitutions. Extensive simulations and large-scale online A/B tests on Taobao platform demonstrate that ReAlloc achieves simultaneous lifts in both pay order and income.
Cite
@article{arxiv.2607.28182,
title = {Multi-channel Uplift Policy Learning},
author = {Changjian Liu and Tianyu Wang and Xiaoxuan Deng and WenTao Zhu and Yuwei Xu and Jungqi Jin and Yong Gao and Chuan Yu and Jian Xu and Bo Zheng},
journal= {arXiv preprint arXiv:2607.28182},
year = {2026}
}