大工至善|大学至真分享 http://blog.sciencenet.cn/u/lcj2212916

博文

[转载]【计算机科学】【2018.06】基于机器学习技术的供应链预测

已有 293 次阅读 2020-6-29 18:01 |系统分类:科研笔记|文章来源:转载

本文为德国班贝克大学的硕士论文,共86页。

 

本论文是与西门子Healthineers合作撰写的。目标是预测X射线系统供应链的未来销售数字。更好地了解未来的销售数字有助于更好地分配资源。该生产线由五个不同的系统组成,所有系统的销售数字都是以单个量进行预测的。提供的历史数据涵盖15年时间,包括180个数据点。这些数据点是与销售有关的每月普查数据,将传统的统计时间序列建模技术与新兴的机器学习方法进行了比较。采用的时间序列建模技术是指数平滑和ARIMA机器学习技术包括建模前馈神经网络和随机森林。所有方法的性能均用平均绝对百分率误差进行测量。所有实现方法的最佳性能来自于扩展的ARIMA模型(ARIMAX,相对误差达到9.55%。此外,本文还包括了一个供应链管理软件工具的实现。

 

This thesis was written in cooperation withSiemens Healthineers. The goal was to predict future sales figures of X-raysystems for the supply chain management. Better knowledge about future salesnumbers enables better allocation of resources. The product line consists offive different systems. Sales figures are predicted for all systems as a singlequantity and also individually. The historic data supplied covered 15 years andconsisted of 180 data points. These data points are a monthly census of salesrelated figures. Traditional time series modeling techniques from statisticswere compared with newly emerging machine learning approaches. The establishedtime series modeling techniques were exponential smoothing and ARIMA. Themachine learning techniques consisted of modeling feedforward neural networksand random forests. The performance of all methods was measured with the meanabsolute percentage error. The best performance of all implemented methodsresulted from an extended ARIMA model (ARIMAX) with a relative error of 9.55%.Moreover, the thesis included implementing a software tool for the supply chainmanagement to make forecasts in practice.

 

1. 引言

2. 理论背景与以前工作回顾

3. 研究方法

4. 评估方法

5. 结论

附录实验


更多精彩文章请关注公众号:205328s611i1aqxbbgxv19.jpg




http://blog.sciencenet.cn/blog-69686-1239898.html

上一篇:[转载]【信息技术】【2015.03】基于深度神经网络的语音识别
下一篇:[转载]【雷达与对抗】【2017.04】多光谱与多时域遥感图像分析的新方法

0

该博文允许注册用户评论 请点击登录 评论 (0 个评论)

数据加载中...

Archiver|手机版|科学网 ( 京ICP备07017567号-12 )

GMT+8, 2020-8-7 00:25

Powered by ScienceNet.cn

Copyright © 2007- 中国科学报社

返回顶部