PulseAugur
实时 10:59:35
English(EN) FreshRetailNet-LT: A Stockout-Annotated Censored Demand Dataset for Latent Demand Recovery and Forecasting in Fresh Retail

新数据集解决审查销售数据以进行零售需求预测

研究人员推出 FreshRetailNet-50K,一个旨在改善易腐零售品需求预测的新型数据集。该数据集解决了审查销售数据带来的挑战,当缺货阻止观察到真实客户需求时就会出现这种情况。通过提供来自近 900 家商店的详细带缺货标注的每小时销售数据,FreshRetailNet-50K 能够更准确地重建潜在需求和进行后续预测,在预测准确性和偏差减少方面显示出显著的改进。 AI

影响 通过解决零售AI的局限性,实现更准确的需求估算和易腐库存优化。

排序理由 该集群包含一篇介绍新数据集和方法的学术论文。[lever_c_demoted from research: ic=1 ai=0.7]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Yangyang Wang, Jiawei Gu, Li Long, Xin Li, Li Shen, Zhouyu Fu, Xiangjun Zhou, Xu Jiang ·

    FreshRetailNet-LT: A Stockout-Annotated Censored Demand Dataset for Latent Demand Recovery and Forecasting in Fresh Retail

    arXiv:2505.16319v3 Announce Type: replace Abstract: Accurate demand estimation is critical for the retail business in guiding the inventory and pricing policies of perishable products. However, it faces fundamental challenges from censored sales data during stockouts, where unobs…