碩士 / 國立政治大學 / 金融學系 / 106 / With globalization, new technology and more complicated financial instruments, the financial market become more volatile, making risk management an inevitable issue. In this paper, we define a major financial crisis event as a "financial stress event." It uses the stock market crash as a criterion for the occurrence of a "financial stress event," and define two different judgment periods of 6-months and 3-months respectively. Using the variables such as interest rate, exchange rate, and asset price, together with the Logistic Regression model, Artificial Neural Network model, and Support Vector Machine, a financial stress model was established to predict the occurrence of “financial stress events” everyday. By using Taiwan Capitalization Weighted Stock Index as empirical evidence, the result shows that regardless of the method, the predictability of 6-months judgment period is better than the 3-months period. Regardless of the length of the judgment period, Support Vector Machine has the highest predictability, followed by Artificial Neural Network model, and Logistic Regression is the weakest.
| Identifer | oai:union.ndltd.org:TW/106NCCU5214020 |
| Date | January 2018 |
| Creators | Chu, Chun-Ya, 朱君亞 |
| Contributors | Lin, Shih-Kuei, Tsai, Yen-Lung, 林士貴, 蔡炎龍 |
| Source Sets | National Digital Library of Theses and Dissertations in Taiwan |
| Language | zh-TW |
| Detected Language | English |
| Type | 學位論文 ; thesis |
| Format | 36 |
Page generated in 0.0021 seconds