Reproduce “TaQFormer: A Treatment-as-Query Transformer with Data-Fusion for Multidimensional Treatment Modeling in Coupon Allocation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jiahong Li, Zeqin Yang, Yu Xiang, Zhifan Jiang, Jingqi Ma, Enzheng Hua, Jixing Xu, Jun Wu and 3 more
TaQFormer models joint discounts across two categories by assigning discount coordinates query tokens that retrieve request context, then combining their representations to predict completion under the offer. It pretrains on observational data and adapts with randomized data. In a 14-day test, business value per user was 1.26% above the production baseline at similar subsidy rates, across 33 feasible offers.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.