完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.author | 蔡興華 | en_US |
dc.contributor.author | Hsing-Hwa Tsai | en_US |
dc.contributor.author | 王克陸 | en_US |
dc.contributor.author | Keh-Luh Wang | en_US |
dc.date.accessioned | 2014-12-12T02:16:59Z | - |
dc.date.available | 2014-12-12T02:16:59Z | - |
dc.date.issued | 2003 | en_US |
dc.identifier.uri | http://140.113.39.130/cdrfb3/record/nctu/#GT009161508 | en_US |
dc.identifier.uri | http://hdl.handle.net/11536/61558 | - |
dc.description.abstract | 本研究的目的在於利用倒傳遞類神經網路建立上市櫃公司的危機預警模型, 用於預測企業是否會在未來的某個年度發生危機。其中危機定義的範圍,限制於上市櫃公司的股票被證交所改列為全額交割股或被處以停止交易時。由於類神經網路模型同時考慮了線性與非線性關係,且其具有高速計算能力、高容記憶能力、學習能力、及容錯能力,相較於傳統的區別分析研究方法,應該會有較高的預測正確率。因此除了建立倒傳遞類神經網路預警模型之外,亦使用相同的樣本建立羅吉斯迴歸預警模型,以比較兩者的預測能力。利用目標年度前一年、前二年、及前三年的財務比率數據,建立的個別模型,倒傳遞類神經網路預警模型的預測正確率較羅吉斯迴歸模型有更佳的預測能力。其預測值與實際值的擬合程度較好,誤差較小。此外,觀察兩種預警模型三種年度模型的預測結果,可以發現愈是遠期的資訊,在預測的效果上愈差。 | zh_TW |
dc.description.abstract | The purpose of this research is to construct an early warning model for financial crisis of the listed companies by using artificial neural network (ANN) with back propagation (BP) algorithm. ANN has error tolerance ability, learning ability, high speed computational ability, and high-volume memorizing ability. It also considers both linear and nonlinear relationship at the same time. To compare with the traditional method, we also adopt logistic regression method to build early warning model. Results show that the accuracy rate in forecasting financial crises is superior for ANN model than that of logistic model. | en_US |
dc.language.iso | zh_TW | en_US |
dc.subject | 類神經網路 | zh_TW |
dc.subject | 倒傳遞 | zh_TW |
dc.subject | 羅吉斯迴歸 | zh_TW |
dc.subject | 財務危機 | zh_TW |
dc.subject | 預警模型 | zh_TW |
dc.subject | Artificial Neural Network | en_US |
dc.subject | Back-Propagation | en_US |
dc.subject | Logistic Regression | en_US |
dc.subject | Financial Crisis | en_US |
dc.subject | Early Warning Model | en_US |
dc.title | 以類神經網路建構上市櫃公司危機預警模型之研究 | zh_TW |
dc.title | The Study of Constructing an Early Warning Model for Financial Crisis by Using Artificial Neural Network Method | en_US |
dc.type | Thesis | en_US |
dc.contributor.department | 高階主管管理碩士學程 | zh_TW |
顯示於類別: | 畢業論文 |