English  |  正體中文  |  简体中文  |  Items with full text/Total items : 49287/83828 (59%)
Visitors : 7149325      Online Users : 70
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/87686


    Title: 類神經網路於財務危機預測模式之應用 : 時間預測變數的比較
    Other Titles: Application of artificial neural network to financial distress prediction model : a comparison of different time-related predictors
    Authors: 林敬凱;Lin, Ching-Kai
    Contributors: 淡江大學統計學系碩士班
    陳景祥;Chen, Ching-Hsiang
    Keywords: 財務危機;預測模式;類神經網路;CART;Financial Distress;Prediction Model;Artificial Neural Network
    Date: 2012
    Issue Date: 2013-04-13 11:32:49 (UTC+8)
    Abstract: 台灣經濟成長從2000年開始衰退,許多企業發生了財務危機,如果可以利用財務比率建構一個穩定的財務危機預測模式,應該可以讓公司決策者提早應變,降低投資者損失。
    關於財務危機方面的預測,大部分的研究者在探討財務危機預測模式時,大都只考慮發生財務危機當年度的資料,若有考慮多個年度或多個季度的資料時,也是把多個年度的資料整合成一個彙整值,或是分別對每個不同期間的資料做預測。 本研究嘗試比較發生財務危機之前三年資訊和單一年度資訊的兩種模式,使用倒傳遞和前饋式類神經網路、以及CART決策樹三種方法作模式準確度的比較。
    研究結果顯示,若考量訓練樣本及測試樣本分類正確率,分析結果發現不論是使用三年的資訊或是只有單一年的資訊的兩種模式都有不錯的準確度。
    In the 2000 years, Taiwan started economic depression that makes many companies have financial distress. If we can use financial ratio to construct a stable prediction model of financial distress, then is can earlier make the decision and decrease the losses.
    About the financial distress prediction, most authors explore this question. Only consider the data on financial distress occurrence current, if consider multiple years or multiple quarters of data that will be integration of multiple year data into an aggregate value or respectively to make predictions for each of the different data period. This study attempts to compare the occurrence of financial distress pass three years information and single year information, uses Back-propagation Network(BPN) and Feed-forward neural network, CART decision tree three methods to compare the model accurate rate.
    By this study, consider the training sample and testing sample which correction rates of classified, the result not only uses three years information but also single year information has the good accurate rate.
    Appears in Collections:[統計學系暨研究所] 學位論文

    Files in This Item:

    File SizeFormat
    index.html0KbHTML83View/Open

    All items in 機構典藏 are protected by copyright, with all rights reserved.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - Feedback