KKT

本页面只读。您可以查看源文件，但不能更改它。如果您觉得这是系统错误，请联系管理员。
====== Applying Deep Learning to the Newsvendor Problem ======

对本文的总体评价为：（1-5分，5分最高）

可参考以下标准：

  * 5分：佳作、开创性成果
  * 4分：合格的优秀论文、可直接接收发表
  * 3分：小改（Minor）后可接收
  * 2分：需要大改（Major）
  * 1分：价值有限，即使修改后亦不能发表
  * 0分：本wiki不收录0分的论文。。。

**有必要时，可以在文中任何地方插入你的签名。**
===== 文献基本信息 =====

==== 标题 ====


==== 作者 ====
  - Afshin Oroojlooyjadid, Lehigh University
  - Lawrence V. Snyder, Lehigh University
  - Martin Takác, Lehigh University


==== 出版年份 ====
2018

==== 来源 ====
ArXiv

==== 关键词 ====


==== 摘要 ====
The newsvendor problem is one of the most basic and widely applied inventory models. There
are numerous extensions of this problem. If the probability distribution of the demand is known,
the problem can be solved analytically. However, approximating the probability distribution is not
easy and is prone to error; therefore, the resulting solution to the newsvendor problem may be not
optimal. To address this issue, we propose an algorithm based on deep learning that optimizes the
order quantities for all products based on features of the demand data. Our algorithm integrates
the forecasting and inventory-optimization steps, rather than solving them separately, as is typically
done, and does not require knowledge of the probability distributions of the demand. Numerical
experiments on real-world data suggest that our algorithm outperforms other approaches, including
data-driven and machine learning approaches, especially for demands with high volatility. Finally, in
order to show how this approach can be used for other inventory optimization problems, we provide
an extension for (r, Q) policies.



==== 引用方式 ====
Oroojlooyjadid, Afshin, Lawrence Snyder, and Martin Takáč. "Applying deep learning to the newsvendor problem." arXiv preprint arXiv:1607.02177 (2016).



==== 链接 ====
  * https://arxiv.org/pdf/1607.02177.pdf
  * https://www.tandfonline.com/doi/pdf/10.1080/24725854.2019.1632502?needAccess=true
  * https://eyun.baidu.com/s/3kWMzwEV

===== 评阅意见 =====

==== 文献简介 ====

1. 论文是关于什么的？[请提供该论文的简要摘要。]

解决多特征报童（Multi-Feature Newsvendor, MFNV）问题的五种常见方法：

  - Estimate-as-Solution (EAS)
  - Separated Estimation and Optimization (SEO)
  - Empirical Quantile Method
  - Integrating ML in Optimization
  - Linear Machine Learning (LML) Method


==== 文献评价 ====


2. 这篇论文的长处和短处是什么？[请以以下角度评述：（a）创新（研究问题、建模、方法等）；（b）相关性（研究问题、发现等）；（c）严谨性（适当的方法、分析的正确性等）]

=== 创新性 ===
研究问题、建模、方法等

=== 相关性 ===
研究问题、发现

=== 严谨性 ===
适当的方法、分析的正确性等
==== 需改改进之处 ====

3.如果有的话，潜在改进的主要地方是什么？[如果这些关键要求和建议能够被适当处理，请重点关注能使文章发表的关键要求和建议。如果你看到不可逾越的障碍，请清楚地描述你的担忧。如果能为编辑和作者提供具体有建设性的意见最好不过了，并在可能的情况下，提出可行的建议。同样，应避免含糊不清和/或含糊不清的批评。]



==== 需要小改的地方 ====

4.如果有的话，潜在改进的微小地方是什么？[再次，请具体说明。]


==== 进一步研究的可能与方向 ====

5.有没有机会做一项新的研究？

==== 其他评价 ====