文化大學機構典藏 CCUR:Item 987654321/51199
English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 46962/50828 (92%)
造访人次 : 12556799      在线人数 : 351
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜寻范围 查询小技巧:
  • 您可在西文检索词汇前后加上"双引号",以获取较精准的检索结果
  • 若欲以作者姓名搜寻,建议至进阶搜寻限定作者字段,可获得较完整数据
  • 进阶搜寻
    主页登入上传说明关于CCUR管理 到手机版


    jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://irlib.pccu.edu.tw/handle/987654321/51199


    题名: 整合網絡資料包絡分析法與人工智慧技術於績效評估與預測
    Performance Assessment and Prediction by Joint Utilization of Network Data Envelopment Analysis and Artificial Intelligence Technique
    作者: 卡奈多(Jose Reynaldo Canales)
    贡献者: 全球商務碩士學位學程碩士班
    关键词: Managerial Performance Forecasting
    Decision Making
    Machine Learning
    Data envelopment Analysis
    日期: 2021
    上传时间: 2023-02-25 11:37:33 (UTC+8)
    摘要: Data envelopment analysis (DEA) has helped us in some many aspects to make our decision making a lot more accurate by providing better criteria selection when it comes to a selection of different combinations for different objectives. However, DEA is lacking of abilities that could observe a large amount of variables. To solve this problem and to identify the key points of successful businesses, this study introduces an advanced decision making scheme that combines stochastic neighbor embedding (SNE) and data envelopment analysis (DEA) to handle the performance measurement task. SNE will be used to condense large amounts into manageable data since SNE is a method that considers every point to be the neighbor with all the points. Any observation made with the data, the DEA will conduct the learning of every key point to reach a point of reference. In addition, this scheme will not only provide a precise evaluation outcome; it will also back it up with a forecast on capability by machine learning. The scheme promises and alternative performance forecasting and evaluation.
    显示于类别:[全球商務學位學程] 博碩士論文

    文件中的档案:

    档案 描述 大小格式浏览次数
    index.html0KbHTML56检视/开启


    在CCUR中所有的数据项都受到原著作权保护.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回馈