Reproduce “A Deep Learning Framework for Quantile Demand Forecasting in E-commerce with Doubly Censored Data” 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
Ziwen Ye, Jiawen Wei, Teng Song, Chen Chen, Guangrui Ma
DPE trains demand quantiles from sales censored by stockouts or promotions, treating each sale as a bound and redistributing probability mass instead of treating it as true demand or discarding it. The paper introduces Extended D-Calibration for doubly censored data. A seven-day online A/B test reports 8% lower overstock at a fixed stockout-SKU ratio, not effects on profit.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.