基于动态成本非对称性与反馈机制的节点级财务优化需求预测
机器学习
2025-12-24 v1
摘要
本文提出一种基于节点特定成本函数非对称性进行预测调整的方法。该模型通过动态将成本非对称性纳入预测误差概率分布，以偏向最低成本情景，从而实现节省。计算节省额，并通过自我调节机制根据观察到的节省幅度来调节调整幅度，使模型能够适应特定场景的条件以及未建模因素，如校准误差或宏观经济动态的变化。最终，经验结果表明，该模型能够实现年节省510万美元。
引用
@article{arxiv.2512.19722,
title = {Node-Level Financial Optimization in Demand Forecasting Through Dynamic Cost Asymmetry and Feedback Mechanism},
author = {Alessandro Casadei and Clemens Grupp and Sreyoshi Bhaduri and Lu Guo and Wilson Fung and Rohit Malshe and Raj Ratan and Ankush Pole and Arkajit Rakshit},
journal= {arXiv preprint arXiv:2512.19722},
year = {2025}
}
备注
Accepted to Amazon internal conference (AFSS). Now sharing with general public. This is submission is replacing a previous submission with the same title: the main paper is now submitted, while previously we submitted a summary