Please use this identifier to cite or link to this item: https://ah.lib.nccu.edu.tw/handle/140.119/69232
題名: 基於 EEMD 與類神經網路方法進行台指期貨高頻交易研究
A Study of TAIEX Futures High-frequency Trading by using EEMD-based Neural Network Learning Paradigms
作者: 黃仕豪
Huang, Sven Shih Hao
貢獻者: 蕭又新
Shiau, Yuo Hsien
黃仕豪
Huang, Sven Shih Hao
關鍵詞: 類神經網路方法
燭型圖(K線圖)
自回歸滑動平均模型
集合經驗模態分解法
高頻交易
平行運算
時間序列分析
大型數據處理
Artificial Neural Networks
Candlestick Charts
Autoregressive Moving Average model
Ensemble Empirical Mode Decomposition
High-Frequency Trading
Parallel Computing
Time series analysis
Big Data Processing
日期: 2013
上傳時間: 25-Aug-2014
摘要: 金融市場是個變化莫測的環境,看似隨機,在隨機中卻隱藏著某些特性與關係。不論是自然現象中的氣象預測或是金融領域中對下一時刻價格的預測, 都有相似的複雜性。 時間序列的預測一直都是許多領域中重要的項目之一, 金融時間序列的預測也不例外。在本論文中我們針對金融時間序列的非線性與非穩態關係引入類神經網路(ANNs) 與集合經驗模態分解法(EEMD), 藉由ANNs處理非線性問題的能力與EEMD處理時間序列信號的優點,並進一步與傳統上使用於金融時間序列分析的自回歸滑動平均模型(ARMA)進行複合式的模型建構,引入燭型圖概念嘗試進行高頻下的台指期貨TAIEX交易。在不計交易成本的績效測試下本研究的高頻交易模型有突出的績效,證明以ANNs、EEMD方法與ARMA組成的混合式模型在高頻時間尺度交易下有相當的發展潛力,具有進一步發展的價值。在處理高頻時間尺度下所產生的大型數據方面,引入平行運算架構SPMD(single program, multiple data)以增進其處理大型資料下的運算效率。本研究亦透過分析高頻時間尺度的本質模態函數(IMFs)探討在高頻尺度下影響台指期貨價格的因素。
Financial market is complex, unstable and non-linear system, it looks like have some principle but the principle usually have exception. The forecasting of time series always an issue in several field include finance. In this thesis we propose several version of hybrid models, they combine Ensemble Empirical Mode Decomposition (EEMD), Back-Propagation Neural Networks(BPNN) and ARMA model, try to improve the forecast performance of financial time series forecast. We also found the physical means or impact factors of IMFs under high-frequency time-scale. For processing the massive data generated by high-frequency time-scale, we pull in the concept of big data processing, adopt parallel computing method ”single program, multiple data (SPMD)” to construct the model improve the computing performance. As the result of backtesting, we prove the enhanced hybrid models we proposed outperform the standard EEMD-BPNN model and obtain a good performance. It shows adopt ANN, EEMD and ARMA in the hybrid model configure for high-frequency trading modeling is effective and it have the potential of development.
參考文獻: [1] B. B. Mandelbrot, “A multifractalwalkdown,” Scientific American, p. 71, 1999.\n[2] F. Black and M. Scholes, “The pricing of options and corporate liabilities,” The jour-\nnal of political economy, pp. 637–654, 1973.\n[3] J. L. Treynor, “How to rate management of investment funds,” Harvard business\nreview, vol. 43, no. 1, pp. 63–75, 1965.\n[4] R. N. Mantegna, H. E. Stanley, et al., An introduction to econophysics: correlations\nand complexity in finance, vol. 9. Cambridge university press Cambridge, 2000.\n[5] A. J. Frost and R. R. Prechter, Elliott wave principle: key to market behavior. Elliott\nWave International, 2005.\n[6] R. N. Elliott, “The wave principle,” New York, 1938.\n[7] H. Kleinert, Path integrals in quantum mechanics, statistics, polymer physics, and\nfinancial markets. World Scientific, 2009.\n[8] M. Chlistalla, B. Speyer, S. Kaiser, and T. Mayer, “High-frequency trading,”\nDeutsche Bank Research, pp. 1–19, 2011.\n[9] B. Biais and P. Woolley, “High frequency trading,” Manuscript, Toulouse University,\nIDEI, 2011.\n[10] S.-S. Chern and J. Simons, “Characteristic forms and geometric invariants,” Annals\nof Mathematics, pp. 48–69, 1974.\n[11] I. Aldridge, High-frequency trading: a practical guide to algorithmic strategies and\ntrading systems. John Wiley & Sons, 2013.\n[12] C. A. Goodhart and M. O’Hara, “High frequency data in financial markets: Issues\nand applications,” Journal of Empirical Finance, vol. 4, no. 2, pp. 73–114, 1997.\n[13] Y. S. Abu-Mostafa and A. F. Atiya, “Introduction to financial forecasting,” Applied\nIntelligence, vol. 6, no. 3, pp. 205–213, 1996.\n[14] 羅華強 and 通信工程, 類神經網路: MATLAB 的應用. 高立, 2011.\n[15] 蘇木春, 張孝德, et al., 機器學習: 類神經網路, 模糊系統以及基因演算法則. 臺\n北市: 全華科技圖書股份有限公司, 1997.\n[16] S. A. Hamid and Z. Iqbal, “Using neural networks for forecasting volatility of s&p\n500 index futures prices,” Journal of Business Research, vol. 57, no. 10, pp. 1116–\n1125, 2004.\n[17] N. E. Huang, Z. Shen, S. R. Long, M. C. Wu, H. H. Shih, Q. Zheng, N.-C. Yen, C. C.\nTung, and H. H. Liu, “The empirical mode decomposition and the hilbert spectrum\nfor nonlinear and non-stationary time series analysis,” Proceedings of the Royal Soci-\nety of London. Series A: Mathematical, Physical and Engineering Sciences, vol. 454,\nno. 1971, pp. 903–995, 1998.\n[18] Z. Wu and N. E. Huang, “A study of the characteristics of white noise using the\nempirical mode decomposition method,” Proceedings of the Royal Society of Lon-\ndon. Series A: Mathematical, Physical and Engineering Sciences, vol. 460, no. 2046,\npp. 1597–1611, 2004.\n[19] I. Kļevecka and J. Lelis, “Pre-processing of input data of neural networks: the case of\nforecasting telecommunication network traffic,” publication. editionName, vol. 104,\npp. 168–178, 2008.\n[20] Y. C. Tsai, “Forecasting electricity consumption as well as gold price by using an\neemd-based back-propagation neural network learning paradigm,” Master’s thesis,\nNational Chengchi University, Taiwan, 2011.\n[21] Y.-H. Wang, C.-H. Yeh, H.-W. V. Young, K. Hu, and M.-T. Lo, “On the computational\ncomplexity of the empirical mode decomposition algorithm,” Physica A: Statistical\nMechanics and its Applications, vol. 400, pp. 159–167, 2014.\n[22] H. Demuth and M. Beale, “Neural network toolbox for use with matlab,” 1993.\n[23] K. Hornik, M. Stinchcombe, and H. White, “Multilayer feedforward networks are\nuniversal approximators,” Neural networks, vol. 2, no. 5, pp. 359–366, 1989.\n[24] M. T. Hagan, H. B. Demuth, M. H. Beale, et al., Neural network design, vol. 1. Pws\nBoston, 1996.\n[25] E. M. Azoff, Neural network time series forecasting of financial markets. John Wiley\n& Sons, Inc., 1994.\n[26] 王奕鈞, “神經網路應用於地籍坐標轉換之研究,” 2005.\n[27] 陈明, MATLAB 神经网络原理与实例精解. 清华大学出版社, 2013.\n[28] P. Whitle, Hypothesis testing in time series analysis, vol. 4. Almqvist & Wiksells,\n1951.\n[29] G. E. Box, G. M. Jenkins, and G. C. Reinsel, Time series analysis: forecasting and\ncontrol. John Wiley & Sons, 2013.\n[30] J. D. Hamilton, Time series analysis, vol. 2. Princeton university press Princeton,\n1994.\n[31] G. E. Box and D. A. Pierce, “Distribution of residual autocorrelations in\nautoregressive-integrated moving average time series models,” Journal of the Amer-\nican statistical Association, vol. 65, no. 332, pp. 1509–1526, 1970.\n[32] R. S. Tsay, Analysis of financial time series, vol. 543. John Wiley & Sons, 2005.\n[33] A. Pole, Statistical arbitrage: algorithmic trading insights and techniques, vol. 411.\nJohn Wiley & Sons, 2008.\n[34] V. Menon and A. E. Trefethen, “Multimatlab integrating matlab with high per-\nformance parallel computing,” in Supercomputing, ACM/IEEE 1997 Conference,\npp. 30–30, IEEE, 1997.\n[35] B. Barney et al., “Introduction to parallel computing,” Lawrence Livermore National\nLaboratory, vol. 6, no. 13, p. 10, 2010.\n[36] T. Hendershott and R. Riordan, “Algorithmic trading and the market for liquidity,”\nJournal of Financial and Quantitative Analysis, vol. 48, no. 04, pp. 1001–1024,\n2013.\n[37] M. Schaden, “Quantum finance,” Physica A: Statistical Mechanics and its Applica-\ntions, vol. 316, no. 1, pp. 511–538, 2002.\n[38] K. Lee and G. Jo, “Expert system for predicting stock market timing using a candle-\nstick chart,” Expert Systems with Applications, vol. 16, no. 4, pp. 357–364, 1999.\n[39] J. H. Fock, C. Klein, and B. Zwergel, “Performance of candlestick analysis on intra-\nday futures data,” The Journal of Derivatives, vol. 13, no. 1, pp. 28–40, 2005.\n[40] S. Nison, Japanese candlestick charting techniques: a contemporary guide to the\nancient investment techniques of the Far East. Penguin, 2001.\n[41] DayTradingCoach, “Candlestick chart course.” http://www.\ndaytradingcoach.com/daytrading-candlestick-course.htm.\n[42] T. Chordia, R. Roll, and A. Subrahmanyam, “Liquidity and market efficiency,” Jour-\nnal of Financial Economics, vol. 87, no. 2, pp. 249–268, 2008.\n[43] J. Brogaard, “High frequency trading and its impact on market quality,” Northwest-\nern University Kellogg School of Management Working Paper, p. 66, 2010.\n[44] W. Hoeffding, “A non-parametric test of independence,” The Annals of Mathemati-\ncal Statistics, pp. 546–557, 1948.\n[45] L. Bachelier, “Théorie de la spéculation,” in Annales scientifiques de l’École Nor-\nmale Supérieure, vol. 17, pp. 21–86, Société mathématique de France, 1900.\n[46] J. M. Karpoff, “The relation between price changes and trading volume: A survey,”\nJournal of Financial and quantitative Analysis, vol. 22, no. 01, pp. 109–126, 1987.\n[47] G. E. Tauchen and M. Pitts, “The price variability-volume relationship on speculative\nmarkets,” Econometrica: Journal of the Econometric Society, pp. 485–505, 1983.\n[48] S.-Y. Chen, C.-C. Lin, P.-H. Chou, and D.-Y. Hwang, “A comparison of hedge ef-\nfectiveness and price discovery between taifex taiex index futures and sgx msci tai-\nwan index futures,” Review of Pacific Basin Financial Markets and Policies, vol. 5,\nno. 02, pp. 277–300, 2002.\n[49] MSCI, “Msci taiwan.” http://www.msci.com/products/indexes/\nlicensing/msci_taiwan/.\n[50] C. Wang and S. Sern Low, “Hedging with foreign currency denominated stock index\nfutures: evidence from the msci taiwan index futures market,” Journal of Multina-\ntional Financial Management, vol. 13, no. 1, pp. 1–17, 2003.\n[51] H.-P. Spahn, From Gold to Euro: On monetary theory and the history of currency\nsystems. Springer, 2001.\n[52] G. Grudnitski and L. Osburn, “Forecasting s&p and gold futures prices: an applica-\ntion of neural networks,” Journal of Futures Markets, vol. 13, no. 6, pp. 631–643,\n1993.\n[53] T. G. Andersen and T. Bollerslev, “Intraday periodicity and volatility persistence in\nfinancial markets,” Journal of empirical finance, vol. 4, no. 2, pp. 115–158, 1997.\n[54] I. S. Abdalla and V. Murinde, “Exchange rate and stock price interactions in emerging\nfinancial markets: evidence on india, korea, pakistan and the philippines,” Applied\nfinancial economics, vol. 7, no. 1, pp. 25–35, 1997.\n[55] C. K. Ma and G. W. Kao, “On exchange rate changes and stock price reactions,”\nJournal of Business Finance & Accounting, vol. 17, no. 3, pp. 441–449, 1990.\n[56] A. Lendasse, E. de Bodt, V. Wertz, M. Verleysen, et al., “Non-linear financial time\nseries forecasting-application to the bel 20 stock market index,” European Journal\nof Economic and Social Systems, vol. 14, no. 1, pp. 81–92, 2000.\n[57] E. T. Li, “Taiex option trading by using eemd-based neural network learning\nparadigm,” Master’s thesis, National Chengchi University, Taiwan, 2011.\n[58] Y. H. Chen, “A study of trading strategies of taiex futures by using eemd-based neural\nnetwork learning paradigms,” Master’s thesis, National Chengchi University, Tai-\nwan, 2013.\n[59] KaplanSchweser, ed., SCHWESERNOTES 2014 CFA LEVEL I BOOK 1: ETHI-\nCAL AND PROFESSIONAL STANDARDS AND QUANTITATIVE METHODS. Ka-\nplan,Inc., 2013.\n[60] D. Kirk, “Nvidia cuda software and gpu parallel computing architecture,” in ISMM,\nvol. 7, pp. 103–104, 2007.\n[61] M. Fatica and W.-K. Jeong, “Accelerating matlab with cuda,” in The High Perfor-\nmance Embedded Computing Workshop, 2007.\n[62] D. Agrawal, S. Das, and A. El Abbadi, “Big data and cloud computing: current state\nand future opportunities,” in Proceedings of the 14th International Conference on\nExtending Database Technology, pp. 530–533, ACM, 2011.
描述: 碩士
國立政治大學
應用物理研究所
100755005
102
資料來源: http://thesis.lib.nccu.edu.tw/record/#G0100755005
資料類型: thesis
Appears in Collections:學位論文

Files in This Item:
File SizeFormat
500501.pdf1.94 MBAdobe PDF2View/Open
Show full item record

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.