| dc.contributor.advisor | 鄭宇庭 | zh_TW |
| dc.contributor.advisor | Cheng, Yu-Ting | en_US |
| dc.contributor.author (Authors) | 管奕錚 | zh_TW |
| dc.contributor.author (Authors) | Guan, Yi-Zheng | en_US |
| dc.creator (作者) | 管奕錚 | zh_TW |
| dc.creator (作者) | Guan, Yi-Zheng | en_US |
| dc.date (日期) | 2022 | en_US |
| dc.date.accessioned | 10-Feb-2022 12:53:19 (UTC+8) | - |
| dc.date.available | 10-Feb-2022 12:53:19 (UTC+8) | - |
| dc.date.issued (上傳時間) | 10-Feb-2022 12:53:19 (UTC+8) | - |
| dc.identifier (Other Identifiers) | G0105354031 | en_US |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/138884 | - |
| dc.description (描述) | 碩士 | zh_TW |
| dc.description (描述) | 國立政治大學 | zh_TW |
| dc.description (描述) | 統計學系 | zh_TW |
| dc.description (描述) | 105354031 | zh_TW |
| dc.description.abstract (摘要) | 匯率本身同時具有線性和非線性的混合特徵，所以單一的線性模型或是非線性模型都無法完美的準確預測匯率的變動。因此本文採用了數種ARCH族類的波動率模型和BP神經元網絡模型及其各自的組合模型，用於研究組合模型是否能提高匯率預測的精準度將2018年1月2日到2020年12月31日的新台幣對美元日匯率數據序列進行轉換後得到匯率的收益率序列，並使用ARCH、GARCH、GJR GARCH的理論方法分別構建了收益率序列的波動率模型，同時考慮了其殘差服從常態分佈，對稱t分佈和有偏t分佈的三種情況，然後用這些模型對匯率收益率進行了預測同時也使用了BP神經網絡模型對匯率收益率序列進行了擬合與預測。最後，本文根據各模型的預測誤差提出了模型組合的方法。並通過誤差檢驗指標證明BP- Skewed-t GJR GARCH的組合模型相比其餘的單一模型和組合模型都具有更高的收益率預測精準度。 | zh_TW |
| dc.description.abstract (摘要) | The exchange rate itself has both linear and non-linear mixed characteristics, so a single linear model or a non-linear model cannot perfectly and accurately predict changes in the exchange rate. Therefore, this article uses several ARCH family volatility models and BP neural network models and their respective combined models to study whether the combined models can improve the accuracy of exchange rate forecastsAfter converting the daily exchange rate data series of New Taiwan Dollar to USD from January 2, 2018 to December 31, 2020, the exchange rate return sequence was obtained, and the exchange rate return sequence was constructed using the ARCH ，GARCH, and GJR GARCH volatility models，also considering the residuals obey the normal distribution, the symmetric t distribution and the biased t distribution, and then use these models to predict the exchange rate return rate and also use the BP neural network model to fitted and predicted exchange rate return rate.Finally, this paper proposes a model combination method based on the prediction error of each model. And through the error test index, it is proved that the BP-Skewed-t GJR GARCH combination model has a higher accuracy of return prediction than the rest of the single model and the combination model. | en_US |
| dc.description.tableofcontents | 第壹章 緒論 1第一節 研究背景與動機 1第二節 研究目的 2第三節 研究架構 4第貳章 文獻探討 6第一節 相关文獻回顧 6第參章 研究方法 8第一節 數據檢驗 8一、 平穩性檢驗 8二、 隨機性檢驗 9三、 非線性檢驗 10第二節 波動率模型 11一、 波動率的定義 11二、 波動率模型的結構 11第三節 ARCH族類模型 12一、 ARCH模型 12二、 GARCH模型 15三、 GJR GARCH模型 17第四節 波動率模型的構建 18一、 ARCH效應檢定 19二、 模型定階 20三、 模型參數估計 21四、 模型驗證 23五、 模型預測 25第五節 神經元網絡模型 27一、人工神經元網絡模型（ANNS） 27二、BP神經元網絡模型 30第六節 模型組合與結果評估 32第肆章 實證分析 35第一節 原始數據處理與檢驗 35第二節 波動率模型的構建與預測 39第三節 BP神經元網絡的的構建與預測 53第四節 組合模型與結果評估 55第伍章 結論與展望 58第陸章 參考文獻 61 | zh_TW |
| dc.format.extent | 2433344 bytes | - |
| dc.format.mimetype | application/pdf | - |
| dc.source.uri (資料來源) | http://thesis.lib.nccu.edu.tw/record/#G0105354031 | en_US |
| dc.subject (關鍵詞) | 波動率模型 | zh_TW |
| dc.subject (關鍵詞) | BP神經元網絡 | zh_TW |
| dc.subject (關鍵詞) | 偏t分佈 | zh_TW |
| dc.subject (關鍵詞) | 組合模型 | zh_TW |
| dc.subject (關鍵詞) | Volatility model | en_US |
| dc.subject (關鍵詞) | BP neural network | en_US |
| dc.subject (關鍵詞) | Skewed-t | en_US |
| dc.subject (關鍵詞) | Combined model | en_US |
| dc.title (題名) | 基於BPNN- GJR GARCH組合模型在新台幣對美元匯率收益率預測中的應用 | zh_TW |
| dc.title (題名) | Application of BPNN-GJR GARCH Combination Model in the Forecast of the Exchange Rate of New Taiwan Dollar to U.S. Dollar | en_US |
| dc.type (資料類型) | thesis | en_US |
| dc.relation.reference (參考文獻) | [1] Allen, H. and Taylor, M.P.Charts. (1990). Noise and Fundamentals in the London Foreign Exchange Market. The Economic Journal, 100,48-60.[2] Andersen. T. G. Bollerslev. T. and Diebold. F. X. (2000). The distribution of exchange rate volatility. Journal of American Statistical Association, 96,42-55[3] Bollerslev. T. (1986). Generalized Autoregressive ConditionalHeteroscedasticity. Journal of Economics, 31(2), 307-327.[4] Bollerslev. T. (1987). A Conditionally Heteroskedastic Time Series Model for Speculative Prices and Rates of Return. Review of Economics and Statistics, 69(3), 542-547.[5] Breen, W. L. R. Glosten. and R. Jagannathan. (1989). Economic Significance of Predictable Variations in Stock Index Returns. Journal of Finance, 44,1177-89.[6] D. E. Rumelhart . G. E. Hinton. and J. L. McClelland. (1986). A General Framework for Parallel Distributed Processing. Parallel distributed processing: explorations in the microstructure of cognition, 46-76[7] Dickey. D.A. and Fuller. W.A. (1979). Distribution of the Estimators for Autoregressive Time Series with a Unit Root. Journal of American Statistical Association, 74, 427-431.[8] E. E. Holmes. M. D. Scheuerell and E. J. Ward. (2019). Applied Time Series Analysis for Fisheries and Environmental Sciences.[9] Engle, R.F. (1982). Autoregressive Conditional Heteroscedasticity withEstimates of the U. K. Inflation. Econometrica, 50(4), 987-1008.[10] Engle, R.F. and Ng.V.K. (1993). Measuring and Testing the Impact of News on Volatility. Journal of Finance, 48(5), 1749-1778.[11] Huseyin Ince. and Theodore. B. Trafalis. (2005). A Hybrid Model for Exchange Rate Prediction. Journal of Decision Support Systems, 42,1054-1062[12] Kenneth, D. West and Donchul Cho. (1995). The predictive Ability of Several Models of Exchange Rate Volatility. Journal of Economics, 69,367-391.[13] Kang S. (1991). An Investigation of the use of Feedforward Neural for Forecasting. Doctoral Dissertation USA: Univ. of Kent State[14] Monica Billio. Domenico Sartore. and Carlo Toffano. (2000). Combining Forecasts: Some Results on Exchange and Interest Rates. The European Journal of Finance, 10,126-145[15] Pacelli Vincenzo. Bevilacqua Vitoantonio. and Azzollini Michele. (2011). An Artificial Neural Network Model to Forecast Exchange Rates. ProQuest, 57-69[16] Spyros Makridakis. and Steven. C. Wheelwright. (1990). Forecasting Methods for Management. International Journal of Forecasting, 6,563-564[17] S. Walczak. (2001). Information Effects on the Accuracy of Neural Network Financial Forecasting. Decision Making: Recent Developments and Worldwide Applications,69-70[18] Taylor S. (1996). Modeling Financial Time Series. John Wiley & Sons, 6,200-285[19] 曹定州(2006). 基於GA_SVR的匯率預測模型研究及分析. 廣東：暨南大學 22-36[20] 宮舒文(2015). 基於GARCH族模型的人民幣匯率波動性分析. 《統計與決策》, 12,45-47[21] 衡亞亞與沐念國(2009). 基於小波分析與BP-GARCH模型的人民幣匯率預測研究. 《軟件導刊》, 146-150[22] 金艷鳳(2013). 基於BP神經網絡的匯率預測模型研究. 湖北：武漢理工大學 36-42[23] 李佳，黃之豪與陳東蘭(2019). 基於GRU神經網路的歐元兌美元匯率預測研究. 《浙江金融》,3,16-18[24] 徐緣圓(2013). BP神經網絡在匯率預測中的應用. 《時代金融》 ,5005(1),147-148[25] 王德全(2009). 外匯風險度量研究—基於GARCH類模型及VAR方法. 《南方金融》[26] 王曉琳(2006). 遺傳演算法與神經網路在匯率預測中的應用. 山東：青島大學 43-48 | zh_TW |
| dc.identifier.doi (DOI) | 10.6814/NCCU202200025 | en_US |
