Publications-Theses
Article View/Open
Publication Export
-
Google ScholarTM
NCCU Library
Citation Infomation
Related Publications in TAIR
題名 基於EEMD與類神經網路建構台指期貨交易策略
A study of Trading Strategies of TAIEX Futures by using EEMD-based Neural Network Learning Paradigms作者 陳原孝
Chen,Yuan Hsiao貢獻者 蕭又新
陳原孝
Chen,Yuan Hsiao關鍵詞 總體經驗模態
類神經網路
自回歸移動平均模型
交易策略
預測模型
Ensemble Empirical Mode Decomposition
Artificial Neural Network
ARMA
Trading strategy
Forecasting model日期 2012 上傳時間 1-Feb-2013 16:55:52 (UTC+8) 摘要 金融市場瞬息萬變，股價漲跌似乎沒有顯著的規則，這意味著股價的行為特徵是不可精確預知和不確定的，為了在市場上增加收益和減少投資風險，研究人員不得不試圖建立一個有效預測金融市場的模型，它可以估算這種不確定性的影響，很可惜的，至今仍然沒有一個模型接近成功的。沒有成功的模型並不代表它是不存在的，相反的，研究人員需要建立更多的預測模型，以提供市場判斷的經驗法則。我們使用ARMA與兩種不同形式的EEMD-ANN去對台灣加權指數期貨做預測值的精確度比較，我們比較了兩種不同的行情：趨勢與震盪。此外，預測出未來市場之價格後，我們使用2種交易策略去做績效測試，本研究希望能夠找到較適合使用在指數預測的預測模型。 另外在本文中，我們也分析影響TAIEX價格波動的因素，透過EEMD，我們可以將其拆解成數具有不同物理意義的本徵模態函數(IMF)，再藉由統計值選出較重要的IMF並分析其意義。
Financial market changes constantly and Stock Price Volatility (SPV) seems to be no significant rules. This means behavioral characteristic of the stock price cannot foresee and uncertain accurately. In order to increase revenue and reduce investment risk in the market, researchers had to try to establish an effective prediction model of financial markets. It can estimate the impact of this uncertainty. It`s a great pity that there is not a model that is close successfully yet. That does not represent it does not exist successful model. Instead, researchers need to establish more predictive models to offer the market to judge the rule of thumb.The forecasting results of TAIEX Index futures by ARMA Model and two types of EEMD-ANN Models were compared in two kinds of markets – trend and fluctuation. In addition, two trading strategies were tested after the future prices are forecasted. The study attempted to identify a suitable forecasting model.Moreover, the factors for price fluctuation of TAIEX were also analyzed in the study. Through EEMD, they could be decomposed to IMFs with various physical meanings and more important IMFs were selected to be analyzed in accordance with the statistic value.參考文獻 Abu-Mostafa Y. S. and Atiya A. F., 1996. Introduction to Financial Forecasting, Applied Intelligence, 6: 205-213.Yoon Youngohc., Swales, George, 1991. Predicting Stock Price Performance: A Neural Network Approach, Proceedings of the Twenty-Fourth Annual Hawaii International Conference on System.Kamijo, K. and Tanigawa, T., 1993. Stock price pattern recognition: a recurrent neural network approach, in Trippi, R. and Truban, E. (eds), Neural Networks in Finance and Investing.Kuan, C. M. White, H., 1994. Artificial neural networks: An econometric perspective, Econometric Reviews, 13, 1-91.Wood, Douglas and Bhaskar.Dasqupta, 1994. Modelling and Index of the French Capital Market, Economic and Financial Computing, Autumn/Winter, pp.119-136En Tzu Li, 2011. TAIEX Option Trading by using EEMD-based Neural Network Learning Paradigm. Master Thesis of Graduate Institute of Applied Physics, College of Science NCCU.Zheng-Hsiu Chu, 2004. On Study of The Relationship between Taiwan Stock Market and The International Stock Markets. Master Thesis of Department of Statistics, College of management NCKU.D. E. Rumelhart and J. L. McClelland, 1986. Parallel Distributed Processing：Explorations in the Microstructure of Cognition, Vol. 1, MA: MITPress.H. A. Rowley, S. Baluja, and T. Kanade, 1998. Neural network-based face detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(1), January 1998.Kaastra, I., Boyd, M., 1996. Designing a neural network for forecasting fi nancial and economic time series. Neurocomputing, 10, 215-236.M. T. Hagan, H. B. Demuth, Neural Network Design, Thomson Learning, 1996.Stent, G. S., 1973. A Physiological Mechanism for Hebb’s Postulate of Learning. PNAS 70 (4), 997–1001.Hush, D. and Horne, B.1993. Progress in supervised neural networks. IEEE Signal Processing Magazine, 10(1):8-39. Gately, E., 1996.Neural Networks for Financial Forecasting. John Wiley, New YorkMartin F. and Aguado J.A., 2003.Wavelet-based ANN approach for transmission line protection, IEEE Trans. Power Delivery, vol.18, no.4, pp.1572-1574.Nayak, P.C., Sudheer, K.P., Rangan, D.M. and Ramasastri, K.S., 2004. Aneuro-fuzzy computing technique for modeling hydrological time series, Journal of Hydrology, 291(1-2): 52-66.Joseph E. Granville, 1960. A Strategy of Daily Stock Market Timing for Maximum Profit. Englewood Cliffs, N. J.: Prentice-Hall, p.155.Kitchin, Joseph., 1923. Cycles and Trends in Economic Factors, Review of Economics and Statistics, The MIT Press, 5 (1), pp. 10-16.Harry S. Dent Jr., 2008. The Great Depression Ahead: How to Prosper in the CrashFollowing the Greatest Boom in History (New York: Free Press, 2008), at17-39.Siegel, J.J., "Stocks for the Long Run", 4nd ed., New York: McGraw-Hill, 1998.Chang-Hsu Liu, 2010. Calendar Anomalies: A Comparative Study of International Equity Markets.Jasemi, M., Kimiagari, A. M. and Memariani, A., 2011. A modern neural network model to do stock market timing on the basis of the ancient investment technique of Japanese Candlestick. Expert Systems with Applications 38, 3884–3890. 描述 碩士
國立政治大學
應用物理研究所
99755005
101資料來源 http://thesis.lib.nccu.edu.tw/record/#G0997550051 資料類型 thesis dc.contributor.advisor 蕭又新 zh_TW dc.contributor.author (Authors) 陳原孝 zh_TW dc.contributor.author (Authors) Chen,Yuan Hsiao en_US dc.creator (作者) 陳原孝 zh_TW dc.creator (作者) Chen,Yuan Hsiao en_US dc.date (日期) 2012 en_US dc.date.accessioned 1-Feb-2013 16:55:52 (UTC+8) - dc.date.available 1-Feb-2013 16:55:52 (UTC+8) - dc.date.issued (上傳時間) 1-Feb-2013 16:55:52 (UTC+8) - dc.identifier (Other Identifiers) G0997550051 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/56891 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 應用物理研究所 zh_TW dc.description (描述) 99755005 zh_TW dc.description (描述) 101 zh_TW dc.description.abstract (摘要) 金融市場瞬息萬變，股價漲跌似乎沒有顯著的規則，這意味著股價的行為特徵是不可精確預知和不確定的，為了在市場上增加收益和減少投資風險，研究人員不得不試圖建立一個有效預測金融市場的模型，它可以估算這種不確定性的影響，很可惜的，至今仍然沒有一個模型接近成功的。沒有成功的模型並不代表它是不存在的，相反的，研究人員需要建立更多的預測模型，以提供市場判斷的經驗法則。我們使用ARMA與兩種不同形式的EEMD-ANN去對台灣加權指數期貨做預測值的精確度比較，我們比較了兩種不同的行情：趨勢與震盪。此外，預測出未來市場之價格後，我們使用2種交易策略去做績效測試，本研究希望能夠找到較適合使用在指數預測的預測模型。 另外在本文中，我們也分析影響TAIEX價格波動的因素，透過EEMD，我們可以將其拆解成數具有不同物理意義的本徵模態函數(IMF)，再藉由統計值選出較重要的IMF並分析其意義。 zh_TW dc.description.abstract (摘要) Financial market changes constantly and Stock Price Volatility (SPV) seems to be no significant rules. This means behavioral characteristic of the stock price cannot foresee and uncertain accurately. In order to increase revenue and reduce investment risk in the market, researchers had to try to establish an effective prediction model of financial markets. It can estimate the impact of this uncertainty. It`s a great pity that there is not a model that is close successfully yet. That does not represent it does not exist successful model. Instead, researchers need to establish more predictive models to offer the market to judge the rule of thumb.The forecasting results of TAIEX Index futures by ARMA Model and two types of EEMD-ANN Models were compared in two kinds of markets – trend and fluctuation. In addition, two trading strategies were tested after the future prices are forecasted. The study attempted to identify a suitable forecasting model.Moreover, the factors for price fluctuation of TAIEX were also analyzed in the study. Through EEMD, they could be decomposed to IMFs with various physical meanings and more important IMFs were selected to be analyzed in accordance with the statistic value. en_US dc.description.tableofcontents 摘要 2Abstract 3List of Contents 4List of Pictures 5List of Tables 6Chapter 1 Introduction 8Chapter 2 Methodology 132.1 Empirical Mode Decomposition (EMD) 132.2 Ensemble Empirical Mode Decomposition (EEMD) 172.3 Artificial Neural Networks (ANNs) 192.4 EEMD-based neural network learning paradigm 242.5 ARMA Model 25Chapter 3 Experimental Details 263.1 Data description 263.2 The Operation of Price 293.3 Statistical measures 313.3 Significant IMFs 333.4 Experiment design 493.5 Performance 54Chapter 4 Algorithmic Trading 614.1 Trading Strategy I 614.2 Trading Strategy II 67Chapter 5 Conclusion 72References 73 zh_TW dc.language.iso en_US - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0997550051 en_US dc.subject (關鍵詞) 總體經驗模態 zh_TW dc.subject (關鍵詞) 類神經網路 zh_TW dc.subject (關鍵詞) 自回歸移動平均模型 zh_TW dc.subject (關鍵詞) 交易策略 zh_TW dc.subject (關鍵詞) 預測模型 zh_TW dc.subject (關鍵詞) Ensemble Empirical Mode Decomposition en_US dc.subject (關鍵詞) Artificial Neural Network en_US dc.subject (關鍵詞) ARMA en_US dc.subject (關鍵詞) Trading strategy en_US dc.subject (關鍵詞) Forecasting model en_US dc.title (題名) 基於EEMD與類神經網路建構台指期貨交易策略 zh_TW dc.title (題名) A study of Trading Strategies of TAIEX Futures by using EEMD-based Neural Network Learning Paradigms en_US dc.type (資料類型) thesis en dc.relation.reference (參考文獻) Abu-Mostafa Y. S. and Atiya A. F., 1996. Introduction to Financial Forecasting, Applied Intelligence, 6: 205-213.Yoon Youngohc., Swales, George, 1991. Predicting Stock Price Performance: A Neural Network Approach, Proceedings of the Twenty-Fourth Annual Hawaii International Conference on System.Kamijo, K. and Tanigawa, T., 1993. Stock price pattern recognition: a recurrent neural network approach, in Trippi, R. and Truban, E. (eds), Neural Networks in Finance and Investing.Kuan, C. M. White, H., 1994. Artificial neural networks: An econometric perspective, Econometric Reviews, 13, 1-91.Wood, Douglas and Bhaskar.Dasqupta, 1994. Modelling and Index of the French Capital Market, Economic and Financial Computing, Autumn/Winter, pp.119-136En Tzu Li, 2011. TAIEX Option Trading by using EEMD-based Neural Network Learning Paradigm. Master Thesis of Graduate Institute of Applied Physics, College of Science NCCU.Zheng-Hsiu Chu, 2004. On Study of The Relationship between Taiwan Stock Market and The International Stock Markets. Master Thesis of Department of Statistics, College of management NCKU.D. E. Rumelhart and J. L. McClelland, 1986. Parallel Distributed Processing：Explorations in the Microstructure of Cognition, Vol. 1, MA: MITPress.H. A. Rowley, S. Baluja, and T. Kanade, 1998. Neural network-based face detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(1), January 1998.Kaastra, I., Boyd, M., 1996. Designing a neural network for forecasting fi nancial and economic time series. Neurocomputing, 10, 215-236.M. T. Hagan, H. B. Demuth, Neural Network Design, Thomson Learning, 1996.Stent, G. S., 1973. A Physiological Mechanism for Hebb’s Postulate of Learning. PNAS 70 (4), 997–1001.Hush, D. and Horne, B.1993. Progress in supervised neural networks. IEEE Signal Processing Magazine, 10(1):8-39. Gately, E., 1996.Neural Networks for Financial Forecasting. John Wiley, New YorkMartin F. and Aguado J.A., 2003.Wavelet-based ANN approach for transmission line protection, IEEE Trans. Power Delivery, vol.18, no.4, pp.1572-1574.Nayak, P.C., Sudheer, K.P., Rangan, D.M. and Ramasastri, K.S., 2004. Aneuro-fuzzy computing technique for modeling hydrological time series, Journal of Hydrology, 291(1-2): 52-66.Joseph E. Granville, 1960. A Strategy of Daily Stock Market Timing for Maximum Profit. Englewood Cliffs, N. J.: Prentice-Hall, p.155.Kitchin, Joseph., 1923. Cycles and Trends in Economic Factors, Review of Economics and Statistics, The MIT Press, 5 (1), pp. 10-16.Harry S. Dent Jr., 2008. The Great Depression Ahead: How to Prosper in the CrashFollowing the Greatest Boom in History (New York: Free Press, 2008), at17-39.Siegel, J.J., "Stocks for the Long Run", 4nd ed., New York: McGraw-Hill, 1998.Chang-Hsu Liu, 2010. Calendar Anomalies: A Comparative Study of International Equity Markets.Jasemi, M., Kimiagari, A. M. and Memariani, A., 2011. A modern neural network model to do stock market timing on the basis of the ancient investment technique of Japanese Candlestick. Expert Systems with Applications 38, 3884–3890. zh_TW
