Publications-Theses
Article View/Open
Publication Export
-
題名 以循環神經網路信號建構交易策略
Constructing the Trading Strategies with Signals in Recurrent Neural Network作者 陳采駿
Chen, Tsai-Chun貢獻者 廖四郎
Liao, Szu-Lang
陳采駿
Chen,Tsai-Chun關鍵詞 循環神經網路
長短期記憶
神經網路
股價指數預測
Recurrent neural network
Long short term memory
Neural network
Price predict日期 2018 上傳時間 23-Jul-2018 16:50:47 (UTC+8) 摘要 過去傳統計量模型使用的模型時，需要先對變數之間的關係，有著深厚的經 驗，了解不同變數之間的因果關係，並且傳統計量模型在預測的時候，大多會 忽略時間序列中間隔很久的重要事件，只考慮到短天期的變數變動情形。 為了可以充分利用多變量時間序列中有用的資訊，並且進一步提高對於預 測台灣加權股價指數的準確度，本文使用深度學習中的循環神經網路，對股價 指數進行多變量的預測，希望能從眾多變數中提取出有效的資訊，並且解決過 去時間序列中忽略間隔較久的重要事件。 台灣加權股價指數被選為本次研究的對象，並且選取循環神經網路以及向 量自我迴歸共 2 個模型，分別使用這兩個模型對股價指數進行預測，並比較這 兩者在預測指數上的表現。最後結果顯示，在我們過去歷史資料中，循環神經 網路的準確度明顯優於傳統的向量自我迴歸模型。
In the past, the models used in traditional financial econometric models need to have a deep experience in the relationship between variables, and understand the causal relationship between different variables. In traditional financial econometric models, most of them ignore long time distance or delays in time series, just focus on the variable change in short period. In order to make the most information in multivariate time series and to further improve the accuracy of forecasting Taiwan`s weighted stock price index, this paper uses the recurrent neural network in deep learning to perform multivariate forecasting on the stock price index in hopes of being able to extracts valid information from variable and resolves important events that were ignored at long time distance in past time series. The Taiwanese weighted stock price index was selected as the subject of this study, and two models of recurrent neural network and vector autoregression were selected. These two models were used to predict the stock price index and compare the two in the forecast index. which performed. The final result shows that in our past historical data, the accuracy of the recurrent neural network is significantly better than the traditional Vector Autoregression model.參考文獻 1. 黃旭淳，國際原油價格對總體經濟變數的影響。2005 年，未出版之碩士論 文，交通大學，經營管理研究所，國際原油價格對總體經濟變數的影響，新 竹。 2. Christian L. Dunis, Xuehuan Huang (2002). Forecasting and trading currency volatility: an application of recurrent neural regression and model combination. Journal of Forecasting, August 2002, Vol.21(5), pp.317-354. 3. Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio(2015). Neural Machine Translation by Jointly Learning to Align and Translate. Cornell University. 4. Erkam Guresena, Gulgun Kayakutlua, Tugrul U.Daim(2011). Using artificial neural network models in stock market index prediction. Expert Systems With Applications, 2011, Vol.38(8), pp.10389-10397 5. Gary Grudnitski, Larry Osburn (1993). Forecasting S&P and gold futures prices: An application of neural networks. Journal of Futures Markets, September 1993, Vol.13(6), pp.631-643 6. Has¸im Sak, Andrew Senior, Franc¸oise Beaufays (2014). Long Short-Term Memory Recurrent Neural Network Architecturesfor Large Scale Acoustic Modeling. Google, USA. 7. John Alberg, Zachary C. Lipton (2017). Improving Factor-Based Quantitative Investing by Forecasting Company Fundamentals. Cornell University. 8. Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, Yoshua Bengio (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. Cornell University. 42 9. Lilian M.de Menezes, Nikolay Y.Nikolaev (2006). Forecasting with genetically programmed polynomial neural networks. International Journal of Forecasting, April-June 2006, Vol.22(2), pp.249-265 10. Mark T.Leung,An-Sing Chen, HazemDaouk (2000). Forecasting exchange rates using general regression neural networks. Computers and Operations Research, 2000, Vol.27(11), pp.1093-1110 11. Melike Bildiricia,Ö zgür Ö merErsin (2009). Improving forecasts of GARCH family models with the artificial neural networks: An application to the daily returns in Istanbul Stock Exchange. Expert Systems With Applications, May 2009, Vol.36(4), pp.7355-7362 12. Mona Ebadi Jalal, Monireh Hosseini and Stefan Karlsson (2016) . Forecasting incoming call volumes in call centers with recurrent Neural Networks. Journal of Business Research, November 2016, Vol.69(11), pp.4811-4814 13. Richard A. Feinberg, Ik‐Suk Kim, Leigh Hokama, Ko de Ruyter, Cherie Keen, (2000). Operational determinants of caller satisfaction in the call center. International Journal of Service Industry Management, 01 May 2000, Vol.11(2), pp.131-141 14. Yu, Tiffany Hui-Kuang & Huarng, Kun-Huang(2008). A bivariate fuzzy time series model to forecast the TAIEX. Expert Systems With Applications, 2008, Vol.34(4), pp.2945-2952. 描述 碩士
國立政治大學
金融學系
105352021資料來源 http://thesis.lib.nccu.edu.tw/record/#G1053520211 資料類型 thesis dc.contributor.advisor 廖四郎 zh_TW dc.contributor.advisor Liao, Szu-Lang en_US dc.contributor.author (Authors) 陳采駿 zh_TW dc.contributor.author (Authors) Chen,Tsai-Chun en_US dc.creator (作者) 陳采駿 zh_TW dc.creator (作者) Chen, Tsai-Chun en_US dc.date (日期) 2018 en_US dc.date.accessioned 23-Jul-2018 16:50:47 (UTC+8) - dc.date.available 23-Jul-2018 16:50:47 (UTC+8) - dc.date.issued (上傳時間) 23-Jul-2018 16:50:47 (UTC+8) - dc.identifier (Other Identifiers) G1053520211 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/118805 - 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) 105352021 zh_TW dc.description.abstract (摘要) 過去傳統計量模型使用的模型時，需要先對變數之間的關係，有著深厚的經 驗，了解不同變數之間的因果關係，並且傳統計量模型在預測的時候，大多會 忽略時間序列中間隔很久的重要事件，只考慮到短天期的變數變動情形。 為了可以充分利用多變量時間序列中有用的資訊，並且進一步提高對於預 測台灣加權股價指數的準確度，本文使用深度學習中的循環神經網路，對股價 指數進行多變量的預測，希望能從眾多變數中提取出有效的資訊，並且解決過 去時間序列中忽略間隔較久的重要事件。 台灣加權股價指數被選為本次研究的對象，並且選取循環神經網路以及向 量自我迴歸共 2 個模型，分別使用這兩個模型對股價指數進行預測，並比較這 兩者在預測指數上的表現。最後結果顯示，在我們過去歷史資料中，循環神經 網路的準確度明顯優於傳統的向量自我迴歸模型。 zh_TW dc.description.abstract (摘要) In the past, the models used in traditional financial econometric models need to have a deep experience in the relationship between variables, and understand the causal relationship between different variables. In traditional financial econometric models, most of them ignore long time distance or delays in time series, just focus on the variable change in short period. In order to make the most information in multivariate time series and to further improve the accuracy of forecasting Taiwan`s weighted stock price index, this paper uses the recurrent neural network in deep learning to perform multivariate forecasting on the stock price index in hopes of being able to extracts valid information from variable and resolves important events that were ignored at long time distance in past time series. The Taiwanese weighted stock price index was selected as the subject of this study, and two models of recurrent neural network and vector autoregression were selected. These two models were used to predict the stock price index and compare the two in the forecast index. which performed. The final result shows that in our past historical data, the accuracy of the recurrent neural network is significantly better than the traditional Vector Autoregression 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、研究方法………………………………………………………… 2 第四節、本文架構………………………………………………………… 2 第貳章、文獻回顧 ……………………………………………………………… 4 第一節、循環神經網路在不同領域的應用 …………………… 4 第二節、相關方法在價格預測上的應用………………………………… 5 第三章、研究方法 ……………………………………………………………… 8 第一節、數據選擇………………………………………………………… 8 第二節、模型設計………………………………………………………… 18 第三節、試驗過程設計…………………………………………………… 27 第四節、衡量方法………………………………………………………… 28 第四章、實證結果 ……………………………………………………………… 33 第一節、策略績效比較…………………………………………………… 33 第二節、混淆矩陣比較…………………………………………………… 38 第五章、結論與建議……………………………………………………………… 39 第一節、文章節論………………………………………………………… 39 第二節、未來研究建議…………………………………………………… 39 參考文獻…………………………………………………………………………… 41 zh_TW dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G1053520211 en_US dc.subject (關鍵詞) 循環神經網路 zh_TW dc.subject (關鍵詞) 長短期記憶 zh_TW dc.subject (關鍵詞) 神經網路 zh_TW dc.subject (關鍵詞) 股價指數預測 zh_TW dc.subject (關鍵詞) Recurrent neural network en_US dc.subject (關鍵詞) Long short term memory en_US dc.subject (關鍵詞) Neural network en_US dc.subject (關鍵詞) Price predict en_US dc.title (題名) 以循環神經網路信號建構交易策略 zh_TW dc.title (題名) Constructing the Trading Strategies with Signals in Recurrent Neural Network en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 1. 黃旭淳，國際原油價格對總體經濟變數的影響。2005 年，未出版之碩士論 文，交通大學，經營管理研究所，國際原油價格對總體經濟變數的影響，新 竹。 2. Christian L. Dunis, Xuehuan Huang (2002). Forecasting and trading currency volatility: an application of recurrent neural regression and model combination. Journal of Forecasting, August 2002, Vol.21(5), pp.317-354. 3. Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio(2015). Neural Machine Translation by Jointly Learning to Align and Translate. Cornell University. 4. Erkam Guresena, Gulgun Kayakutlua, Tugrul U.Daim(2011). Using artificial neural network models in stock market index prediction. Expert Systems With Applications, 2011, Vol.38(8), pp.10389-10397 5. Gary Grudnitski, Larry Osburn (1993). Forecasting S&P and gold futures prices: An application of neural networks. Journal of Futures Markets, September 1993, Vol.13(6), pp.631-643 6. Has¸im Sak, Andrew Senior, Franc¸oise Beaufays (2014). Long Short-Term Memory Recurrent Neural Network Architecturesfor Large Scale Acoustic Modeling. Google, USA. 7. John Alberg, Zachary C. Lipton (2017). Improving Factor-Based Quantitative Investing by Forecasting Company Fundamentals. Cornell University. 8. Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, Yoshua Bengio (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. Cornell University. 42 9. Lilian M.de Menezes, Nikolay Y.Nikolaev (2006). Forecasting with genetically programmed polynomial neural networks. International Journal of Forecasting, April-June 2006, Vol.22(2), pp.249-265 10. Mark T.Leung,An-Sing Chen, HazemDaouk (2000). Forecasting exchange rates using general regression neural networks. Computers and Operations Research, 2000, Vol.27(11), pp.1093-1110 11. Melike Bildiricia,Ö zgür Ö merErsin (2009). Improving forecasts of GARCH family models with the artificial neural networks: An application to the daily returns in Istanbul Stock Exchange. Expert Systems With Applications, May 2009, Vol.36(4), pp.7355-7362 12. Mona Ebadi Jalal, Monireh Hosseini and Stefan Karlsson (2016) . Forecasting incoming call volumes in call centers with recurrent Neural Networks. Journal of Business Research, November 2016, Vol.69(11), pp.4811-4814 13. Richard A. Feinberg, Ik‐Suk Kim, Leigh Hokama, Ko de Ruyter, Cherie Keen, (2000). Operational determinants of caller satisfaction in the call center. International Journal of Service Industry Management, 01 May 2000, Vol.11(2), pp.131-141 14. Yu, Tiffany Hui-Kuang & Huarng, Kun-Huang(2008). A bivariate fuzzy time series model to forecast the TAIEX. Expert Systems With Applications, 2008, Vol.34(4), pp.2945-2952. zh_TW dc.identifier.doi (DOI) 10.6814/THE.NCCU.MB.019.2018.F06 -
