學術產出-學位論文
文章檢視/開啟
書目匯出
-
題名 金融壓力事件預警模型：類神經網路、支援向量機與羅吉斯迴歸之比較
Financial Stress Model：Comparison of Artificial Neural Network, Support Vector Machine and Logistic Regression作者 朱君亞
Chu, Chun-Ya貢獻者 林士貴<br>蔡炎龍
Lin, Shih-Kuei<br>Tsai, Yen-Lung
朱君亞
Chu, Chun-Ya關鍵詞 金融情勢指數
金融壓力事件預警模型
羅吉斯迴歸模型
類神經網路模型
支援向量機
Financial conditions Index
Financial stress model
Logistic regression
Artificial neural network
Support vector machine日期 2018 上傳時間 4-七月-2018 14:45:43 (UTC+8) 摘要 全球化浪潮、科技進步與金融商品日趨複雜等原因，讓金融商品價格容易在短時間內發生大幅波動，也使得風險管理成為不可避免的議題。本文遂針對重大金融危機事件做出定義，稱之為「金融壓力事件」，以股市大跌作為「金融壓力事件」是否發生的判定標準，且分別針對6個月與3個月的兩種不同判定期間做出定義。再以利率、匯率、資產價格等變數，搭配羅吉斯迴歸模型、類神經網路模型與支援向量機，建立金融壓力事件預警模型，每日針對是否發生「金融壓力事件」進行預測。本研究以台灣加權股價指數實證，實證結果顯示，不論哪一種方法，判定期間為6個月的預測結果都優於判定期間為3個月；不論判定期間長短，都是支援向量機預測能力最好，其次為類神經網路模型，羅吉斯迴歸則較弱。
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.參考文獻 中文文獻[1] 王翎聿（2015），應用倒傳遞類神經網路與支援向量機預測加權股價指數，國防大學管理學院財務管理學系碩士班碩士論文。[2] 呂奇傑、李天行、高人龍、黃敏菁（2009），支援向量機與支援向量迴歸於財務時間序列預測之應用，數據分析，第4卷第2期，35-56。[3] 張天惠（2012），我國金融情勢指數與總體經濟預測，〈中央銀行季刊〉，第34卷第2期，11-42。[4] 黃華山與邱一薰（2005）類神經網路預測台灣50 股價指數之研究，資訊、科技與社會學報，第5卷第2期，19-42。[5] 葉怡成（2003），類神經網路模式應用與實作，臺北市：儒林。英文文獻[1] Cortes, C. and Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273-297.[2] Gauthier, C., Graham, C., and Liu, Y. (2004). Financial Conditions Indexes for Canada. Bank of Canada Working Paper 2004, 22.[3] Goodhart, C. and Hofmann, B. (2001). Asset Prices, Financial Conditions, and the Transmission of Monetary Policy. Paper prepared for the conference on Asset Prices, Exchange rates, and Monetary Policy, Stanford University, March 2-3.[4] Hatzius, J., Hooper, P., Mishkin, F. S., Schoenholtz, K. L., and Watson, M. W. (2010). Financial Conditions Index: A Fresh Look after the Financial Crisis. NBER Working Paper 16150.[5] Hsieh, L. F., Hsieh, S. C., and Tai, P. H. (2011). Enhanced Stock Price Variation Prediction via DOE and BPNN-based Optimization. Expert Systems with Applications 38, 14178-14184.[6] Hsu, C. W., Chang, C. C., and Lin, C. J. (2003). A Practical Guide to Support Vector Classification. Available at http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf.[7] Huang, W., Nakamoria, Y., and Wang, S. Y. (2004). Forecasting Stock Market Movement Direction with Support Vector Machine. Computers & Operations Research 32, 2513-2522.[8] Kara, Y., Boyacioglu, M. A., and Baykan, Ö . K. (2011). Predicting Direction of Stock Price Index Movement using Artificial Neural Networks and Support Vector Machines: The Sample of the Istanbul Stock Exchange. Expert Systems with Applications 38, 5311-5319.[9] Kim, K. J. (2003). Financial Time Series Forecasting Using Support Vector Machines. Neurocomputing 55, 307-319.[10] Rumelhart, D. E., Hinton, G. E., and Williams, R. J. (1986). Learning Representations by Back-propagating Errors. Nature, 323, 533-536.[11] Silvers, D. and Slavkin, H. (2009). The Legacy of Deregulation and the Financial Crisis: Linkages Between Deregulation in Labor Markets, Housing Finance Markets, and the Broader Financial Markets. Journal of Business & Technology Law 4, 2, 301.[12] Skaarup, M., Duschek-Hansen, C., and Nielsen, S. (2010). A Financial Conditions Index for Denmark. Working Paper no 23/2010, The Danish Ministry of Finance.[13] Svozil, D., KvasniEka, V., and Pospichal, J. (1997). Introduction to Multi-layer Feed-Forward Neural Networks. Chemometrics and Intelligent Laboratory Systems 39, 43-62. 描述 碩士
國立政治大學
金融學系
105352011資料來源 http://thesis.lib.nccu.edu.tw/record/#G0105352011 資料類型 thesis dc.contributor.advisor 林士貴<br>蔡炎龍 zh_TW dc.contributor.advisor Lin, Shih-Kuei<br>Tsai, Yen-Lung en_US dc.contributor.author (作者) 朱君亞 zh_TW dc.contributor.author (作者) Chu, Chun-Ya en_US dc.creator (作者) 朱君亞 zh_TW dc.creator (作者) Chu, Chun-Ya en_US dc.date (日期) 2018 en_US dc.date.accessioned 4-七月-2018 14:45:43 (UTC+8) - dc.date.available 4-七月-2018 14:45:43 (UTC+8) - dc.date.issued (上傳時間) 4-七月-2018 14:45:43 (UTC+8) - dc.identifier (其他 識別碼) G0105352011 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/118357 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 金融學系 zh_TW dc.description (描述) 105352011 zh_TW dc.description.abstract (摘要) 全球化浪潮、科技進步與金融商品日趨複雜等原因，讓金融商品價格容易在短時間內發生大幅波動，也使得風險管理成為不可避免的議題。本文遂針對重大金融危機事件做出定義，稱之為「金融壓力事件」，以股市大跌作為「金融壓力事件」是否發生的判定標準，且分別針對6個月與3個月的兩種不同判定期間做出定義。再以利率、匯率、資產價格等變數，搭配羅吉斯迴歸模型、類神經網路模型與支援向量機，建立金融壓力事件預警模型，每日針對是否發生「金融壓力事件」進行預測。本研究以台灣加權股價指數實證，實證結果顯示，不論哪一種方法，判定期間為6個月的預測結果都優於判定期間為3個月；不論判定期間長短，都是支援向量機預測能力最好，其次為類神經網路模型，羅吉斯迴歸則較弱。 zh_TW dc.description.abstract (摘要) 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. en_US dc.description.tableofcontents 第一章 緒論 1第一節 研究背景與動機 1第二節 金融壓力事件定義 2第三節 研究目的 3第二章 文獻回顧 4第一節 金融情勢指數使用變數 4第二節 金融市場預測之研究方法 5第三章 研究方法 8第一節 迴歸模型 8第二節 類神經網路模型 9第三節 支援向量機 12第四章 實證資料 17第一節 資料期間 17第二節 變數選取 17第三節 模型建構 19第四節 超參數設定 19第五章 實證結果 26第一節 羅吉斯迴歸模型實證結果 27第二節 類神經網路模型實證結果 29第三節 支援向量機實證結果 31第四節 各模型結果比較 31第六章 結論 33參考文獻 35中文文獻 35英文文獻 35 zh_TW dc.format.extent 1585448 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0105352011 en_US dc.subject (關鍵詞) 金融情勢指數 zh_TW dc.subject (關鍵詞) 金融壓力事件預警模型 zh_TW dc.subject (關鍵詞) 羅吉斯迴歸模型 zh_TW dc.subject (關鍵詞) 類神經網路模型 zh_TW dc.subject (關鍵詞) 支援向量機 zh_TW dc.subject (關鍵詞) Financial conditions Index en_US dc.subject (關鍵詞) Financial stress model en_US dc.subject (關鍵詞) Logistic regression en_US dc.subject (關鍵詞) Artificial neural network en_US dc.subject (關鍵詞) Support vector machine en_US dc.title (題名) 金融壓力事件預警模型：類神經網路、支援向量機與羅吉斯迴歸之比較 zh_TW dc.title (題名) Financial Stress Model：Comparison of Artificial Neural Network, Support Vector Machine and Logistic Regression en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 中文文獻[1] 王翎聿（2015），應用倒傳遞類神經網路與支援向量機預測加權股價指數，國防大學管理學院財務管理學系碩士班碩士論文。[2] 呂奇傑、李天行、高人龍、黃敏菁（2009），支援向量機與支援向量迴歸於財務時間序列預測之應用，數據分析，第4卷第2期，35-56。[3] 張天惠（2012），我國金融情勢指數與總體經濟預測，〈中央銀行季刊〉，第34卷第2期，11-42。[4] 黃華山與邱一薰（2005）類神經網路預測台灣50 股價指數之研究，資訊、科技與社會學報，第5卷第2期，19-42。[5] 葉怡成（2003），類神經網路模式應用與實作，臺北市：儒林。英文文獻[1] Cortes, C. and Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273-297.[2] Gauthier, C., Graham, C., and Liu, Y. (2004). Financial Conditions Indexes for Canada. Bank of Canada Working Paper 2004, 22.[3] Goodhart, C. and Hofmann, B. (2001). Asset Prices, Financial Conditions, and the Transmission of Monetary Policy. Paper prepared for the conference on Asset Prices, Exchange rates, and Monetary Policy, Stanford University, March 2-3.[4] Hatzius, J., Hooper, P., Mishkin, F. S., Schoenholtz, K. L., and Watson, M. W. (2010). Financial Conditions Index: A Fresh Look after the Financial Crisis. NBER Working Paper 16150.[5] Hsieh, L. F., Hsieh, S. C., and Tai, P. H. (2011). Enhanced Stock Price Variation Prediction via DOE and BPNN-based Optimization. Expert Systems with Applications 38, 14178-14184.[6] Hsu, C. W., Chang, C. C., and Lin, C. J. (2003). A Practical Guide to Support Vector Classification. Available at http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf.[7] Huang, W., Nakamoria, Y., and Wang, S. Y. (2004). Forecasting Stock Market Movement Direction with Support Vector Machine. Computers & Operations Research 32, 2513-2522.[8] Kara, Y., Boyacioglu, M. A., and Baykan, Ö . K. (2011). Predicting Direction of Stock Price Index Movement using Artificial Neural Networks and Support Vector Machines: The Sample of the Istanbul Stock Exchange. Expert Systems with Applications 38, 5311-5319.[9] Kim, K. J. (2003). Financial Time Series Forecasting Using Support Vector Machines. Neurocomputing 55, 307-319.[10] Rumelhart, D. E., Hinton, G. E., and Williams, R. J. (1986). Learning Representations by Back-propagating Errors. Nature, 323, 533-536.[11] Silvers, D. and Slavkin, H. (2009). The Legacy of Deregulation and the Financial Crisis: Linkages Between Deregulation in Labor Markets, Housing Finance Markets, and the Broader Financial Markets. Journal of Business & Technology Law 4, 2, 301.[12] Skaarup, M., Duschek-Hansen, C., and Nielsen, S. (2010). A Financial Conditions Index for Denmark. Working Paper no 23/2010, The Danish Ministry of Finance.[13] Svozil, D., KvasniEka, V., and Pospichal, J. (1997). Introduction to Multi-layer Feed-Forward Neural Networks. Chemometrics and Intelligent Laboratory Systems 39, 43-62. zh_TW dc.identifier.doi (DOI) 10.6814/THE.NCCU.MB.013.2018.F06 -
