簡易檢索 / 詳目顯示

回結果列表
研究生： 李大聖
Dah-Sheng Lee
論文名稱： 金融時間序列預測之調適性模型選擇
Adaptive switching on model selection of financial time series
指導教授： 李漢銘
Hahn-Ming Lee
口試委員: 何正信
Cheng-Seen Ho
何建明
Jan-Ming Ho
鮑興國
Hsing-Kuo Pao
黃淇竣
Chi-Chun Huang
學位類別： 碩士
Master
系所名稱： 電資學院 - 資訊工程系
Department of Computer Science and Information Engineering
論文出版年： 2005
畢業學年度： 93
語文別： 英文
論文頁數： 89
中文關鍵詞： 金融時間序列 、移動視窗 、非穩定性質
外文關鍵詞： Financial, moving window, non-stationary
相關次數： 點閱：304  下載：3 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 金融時間序列是一種不具線性(non-linear)與平穩性質(non-stationary)且包含了大量雜訊的時間序列。當我們要正確的預測金融時間序列時必須同時考慮上述三個性質的影響，並且要選擇一個恰當的預測模型。因此，預測模型的選擇可說是正確預測金融時間序列的關鍵點之一。但是模型選擇一直以來存在著精確性與處理時效不可兼得的問題，尤其是在金融時間序列這類複雜度高的資料。因此，如何在一個及時(real-time)的金融預測模型選擇方法中兼顧精確性與處理時效是研究上的一大挑戰。

    根據艾略特於西元1938年所提出來的波浪理論，他將市場上的價格趨勢，歸納出幾個不斷反覆出現的型態。因此，過去的歷史資料分析能夠協助我們選擇預測模型的對應參數值。我們根據波浪理論提出了一個以重覆性特徵為基礎的模型選擇方法，並將此方法與移動視窗法結合。使得預測模型可視金融時間序列在不同時間的特性變化作最佳化的調適，這樣的方法也同時減少了非平穩性質對於預測模型的不良影響。最後，實驗證實了當決策支援系統搭配我們所建議的模型選擇與金融時間序列預測方法，能在真正的股票市場中獲利。

    Financial time series are non-linear, non-stationary data. They also contain a huge amount of noise. To obtain high accuracy prediction results, those properties must be concerned simultaneously; also a proper financial prediction model must be selected carefully. However, the model selection is a trade-off between the time complexity and the accuracy. Therefore, to balance the process time and the accuracy is a challenge for the read-time financial model selection.

    The cycle of stock fluctuated trends theoretically repeats themselves according to the wave theory (Nalph Nelson Eilliott, 1938). Based on this, we propose a repeat-pattern based financial model selection method. The model selection method can cooperate with the moving-window based training algorithm, and thus to accomplish an adaptive model selection method. The adaptive on model selection method is able to make a financial prediction model more stable. That results in our proposed method based decision support system can be applied to the real stock market efficiently and obtain good performance, as indicated from the experiment results.

    Abstract…………………………………………………………Ⅰ Acknowledgements……………………………………………Ⅲ Contents…………………………………………………………Ⅳ List of Figures…………………………………………………Ⅵ List of Tables……………………………………………………Ⅶ Chap 1 Introduction……………………………………………………1 1.1Motivation………………………………………………………………1 1.2The challenges of financial model selection and time series modeling...3 1.2.1Non-stationary property handling…………………………………………3 1.2.2Applicability of the moving-window based training algorithm…………4 1.3Goals……………………………………………………………………5 1.4Limitations of this work………………………………………………...5 1.5Outline of the Thesis……………………………………………………6 Chap 2 Background Knowledge…………………………………………7 2.1An overview of financial time series…………………………………...7 2.2Moving-window based training algorithm……………………………13 2.3Pattern-matching methodologies………………………………………15 Chap3 Adaptive switching on model selection of financial time series………20 3.1The Concept of adaptive switching on model selection of financial time series………21 3.2System framework of adaptive switching on model selection of financial time series…23 3.2.1Time-weight based module repository…………………………………………24 3.2.1.1Fixed-period model switching strategy………………………………...25 3.2.1.2Definition of parameters………………………………………………27 3.2.1.3Segmentation of historical financial time series………………………28 3.2.1.4Module repository building……………………………………………29 3.2.2Adaptive financial model selector……………………………………………31 3.2.2.1Curve matching unit……………………………………………………33 3.2.2.2Time-weight identifying unit……………………………………………34 3.2.2.3Module Selector…………………………………………………………36 3.3Characteristics of proposed method……………………………………38 3.4Comparison with Other Methods………………………………………41 Chap 4 Experiments……………………………………………………45 4.1Setting of experiments…………………………………………………45 4.1.1Implementation of Support Vector Regression………………………………47 4.1.2Implementation of time-weight based module repository……………………48 4.2Experiment results……………………………………………………48 4.2.1Sensitivity analysis……………………………………………………………49 4.2.2Statistic characteristics and evaluation………………………………………54 4.2.3Performance evaluation………………………………………………………..62 Chap 5 Conclusion and Further Work…………………………………75 5.1Discussion……………………………………………………………75 5.2Conclusion……………………………………………………………79 5.3Further Work…………………………………………………………80 REFERENCES.................................................83

    [1] D. Zhand, L. Zhou, “Discovering Golden Nuggets: Data Mining in Financial Application,” IEEE Transactions on System, Man, and Cybernetics, Part A, 2004.
    [2] A.F. Shapiro, “Capital Market Application of Neural Networks, Fuzzy Logic and Genetic Algorithms,” In proceedings of the 13th International AFIR Colloquium, vol. 1, pp. 493-514, 2003.
    [3] V. Bruce, T. Clarence, “A Survey of the Application of Soft Computing to Investment and Financial Trading,” In Proceedings of the 8th Australian and New Zealand Intelligent Information Systems Conference (ANZIIS 2003) on Sydney, Australia, pp. 10-12, December 2003.
    [4] V. Dhar, D. Chou, “A Comparison of Nonlinear Methods for Prediction Earning Surprise and Returns,” IEEE Transactions on Neural Networks, vol. 12, July 2001.
    [5] E.W. Saad, D.V. Prokhorov, D.C. Wunsch, II, “Comparative Study of Stock Trend Prediction Using Time Delay, Recurrent and Probabilistic Neural Networks,” IEEE Transactions on Neural Networks, vol. 9, no. 6, pp. 1456-1470, November 1998.
    [6] Y.H. Gu, 2003, Fundamental Analysis, The Business Weekly Publication Group, Taiwan, in Chinese Edition.
    [7] J.H. Liao, 2004, Technical Analysis, PC Home Publication Group, Taiwan, in Chinese Edition.
    [8] Y.J. Wu, Grey-based Stock Selection System, Master thesis, National Taiwan University of Science and Technology, 2002.
    [9] A. Skabar, I. Cloete, “Neural Networks and Financial Trading and the Efficient Markets Hypothesis,” In Proceedings of Australasian Computer Science Conference, pp. 241-249, 2002.
    [10] C.H. Chen, An intelligent stock trading decision support system using adaptive rule-based neural network, Master thesis, National Taiwan University, 1994.
    [11] G.A. Torben, J. Lund, “Estimating continuous-time stochastic volatility models of the short-term interest rate,” Journal of Econometrics, vol. 77, pp. 343-378, 1997.
    [12] H.T. Peng, H.M. Lee, J.M. Ho, “TradingDecisionMaker: Stock Trading Decision by Price Series Smoothing and Tendency Transition Inference,” In Proceedings of IEEE International Conference on e-Technology, e-Commerce and e-Service, 2005.
    [13] R.S. Tsay, 2002, Analysis of Financial Time Series, John Wiley & Sons, Inc., New Work.
    [14] R.S. Pindyck, 1998, Econometric models and economics forecasts, McGraw-Hill, Inc., New Work.
    [15] K. Fu, W.H. Xu, “Training neural network with genetic algorithms for forecasting the stock price index,” In Proceedings of IEEE International Conference on Intelligent Processing Systems, vol. 1, pp. 401-403, 1997.
    [16] N. Baba, N. Inoue, H. Asakawa, “Utilization of neural networks and GAs for constructing reliable decision support systems to deal stocks,” In Proceedings of IJCNN 2000, vol. 5, 2000.
    [17] R.J. Kuo, C.H. Chen, Y.C. Hwang, “An intelligent stock trading decision support system through integration of genetic algorithm based fuzzy neural network and artificial neural network,” Fuzzy Sets and Systems, vol. 118, Issue 1, pp. 21-45, February 16, 2001.
    [18] S.Y. Tseng, “Knowledge Discovery with Self-Organizing Map in Investment Strategy,” In Proceedings of the 7th Conference on Artificial Intelligence and Applications (TAAI 2002), 2002.
    [19] Y.F. Wang, “On-Demand Forecasting of Stock Prices Using a Real-Time Predictor,” IEEE Transactions on Knowledge and Data Engineering, vol. 15, no 4, July 2003.
    [20] A. Fan, M. Palaniswami, “Stock selection using support vector machines,” In Proceedings of IJCNN 2001, vol.3, pp. 1793-1798, 2001.
    [21] L.J. Cao, E.H. Tay, “Support Vector Machine With Adaptive Parameters in Financial Time Series Forecasting,” IEEE Transactions on Neural Networks, vol. 14, no. 6, pp. 1506-1518, November 2003.
    [22] J.T. Yao, C.L. Tan, “A Study on Training Criteria for Financial Time Series Foreasting,” In Proceedings of International Conference on Neural Information on Shanghai, China, pp.772-777, 2001.
    [23] A.N. Refenes, Y. Bentz, D.W. Bunn, A.N. Burgess, A.D. Zapranis, “Financial time series modeling with discounted least squares backpropagation,” Neural Computation, vol. 14, pp. 123-138, 1997.
    [24] H.B. Hwarng, H.T. Ang, “A simple neural network for ARMA (p,q) time series,” omega, vol. 29, pp. 319-333, 2001.
    [25] H.B. Hwarng, “Insights into neural-network forecasting of time series corresponding to ARMA (p,q) structures,” omega, vol. 29, pp. 273-289, 2001.
    [26] W.C. Kao, K.M. Chung, C.L. Sun, C.J. Lin, “Decomposition Method for Linear Support Vector Machines,” Neural Computation, vol. 16, pp. 1689-1704, 2004.
    [27] C.M. Chen, H.M. Lee, “An Efficient Gradient Forecasting Search Method Utilizing the Discrete Difference Equation Prediction Model,” Applied Intelligence, vol. 16, no. 1, pp. 43-58, 2002.
    [28] J. Rees, G.J. Koehler, “Modeling Search in Group Decision Support Systems,” IEEE Transactions on System, Man, and Cybernetics, PART C, vol. 34, no. 3, August 2004.
    [29] P.W. Chen, J.Y. Wang, H.M. Lee, “Model Selection of SVMs Using GA Approach,” In Proceedings of IJCNN 2004, 2004.
    [30] R. Sindelar, R. Babuska, “Input Selection for Nonlinear Regression Models,” IEEE Transactions on Fuzzy Systems, vol. 12, no. 5, pp. 688-696, October 2004.
    [31] Y.Y. Ou, C.Y. Chen, S.C. Hwang, Y.J. Oyang, “Expediting Model Selection for Support Vector Machines Based on Data Reduction,” In Proceedings of IEEE International Conference on Systems, Man and Cybernetics, 2003.
    [32] Y.J. Oyang, S.C. Hwang, Y.Y. Ou, C.Y. Chen, Z.W. Chen, “Data Classification with Radial Basis Function Networks Based on a Novel Kernel Density Estimation Algorithm,” IEEE Transactions on Neural Networks, pp. 225-236, 2005.
    [33] J. Yao, C.L. Tan, “A Study on Training Criteria for Financial Time Series Forecasting,” In Proceedings of International Conference on Neural Information on Shanghai, China, pp. 772-777, November 14-18, 2001.
    [34] M.W. Chang, C.J. Lin, “Leave-one-out Bounds for Support Vector Regression Model Selection,” Neural Computation, vol. 17, pp. 1188-1222, 2005.
    [35] J.H. Lee, Model Selection of the Bounded SVM Formulation Using the RBF Kernel, PhD thesis, Nation Taiwan University, 2001.
    [36] K.H. Lee, “Model Selection for Neural Network Classification,” Journal of Classification, 2001.
    [37] M.W. Chang, C.J. Lin, “Analysis of switching dynamics with competing support vector machines,” IEEE Transactions on Neural Networks, vol. 15, no. 3, pp. 720-727, 2004.
    [38] S.S. Keerthi, C.J. Lin, “Asymptotic Behaviors of Support Vector Machines with Gaussian Kernel,” Neural Computation, vol. 15, pp. 1667-1689, 2003.
    [39] M.J. Pring, 2002, How to Select Stock Using Technical Analysis, McGraw-Hill, New York.
    [40] R. Bensignor, 2003, NEW THINKING IN Technical Analysis, BLOOMBERG PRESS, New York.
    [41] F.L. Chung, T.C. Fu, V. Ng, W.P. Robert, “An Evolutionary Approach to Pattern-Based Time Series Segmentation,” IEEE Transactions on Evolutionary Computation, vol. 8, pp. 471-489, October 2004.
    [42] T.C. Fu, F.L. Chung, V. Ng, R. Luk, “Evolutionary segmentation of financial time series into subsequences,” In Proceedings of the 2001 Congress on Evolutionary Computation (CEC 2001) on Seoul, Korea, 2001.
    [43] C.T. Yang, Time-Series Classification: Technique Development and Empirical Evaluation, Master thesis, National Sun Yat-sen University, 2001.
    [44] A. Lendasse, E. de Bodt, V. Wertz, M. Verleysen, “Non-linear financial time series forecasting - Application to the Bel 20 stock market index,” European Journal of Economic and Social Systems, vol. 14, no. 1, pp. 81-91, 2000.
    [45] R. Agrawal, C. Faloutsos, A. Swami, “Efficient Similarity Search in Sequence Databases,” In Proceedings of the 4th International Conference on Foundations of Data Organization and Algorithms, pp. 69-84, October 1993.
    [46] C. Faloutsos, M. Ranganathan, Y. Manolopoulos, “Fast Subsequence Matching in Time-Series Databases,” In Proceedings of the 1994 ACM SIGMOD International Conference on Management of Data on Minneapolis, MN, pp. 419-429, May 1994.
    [47] R. Agrawal, K. Lin, H.S. Sawhney, K. Shim, “Fast Similarity Search in the Presence of Noise, Scaling and Translation in Time-Series Databases,” In Proceedings of the 21st International Conference on Very Large Data Bases on Zurich, Switzerland, September 1995.
    [48] C.C. Chang, C.J. Lin, August 2002, LIBSVM: a Library for Support Vector Machine, Nation Taiwan University,available at http://www.csie.ntu.edu.tw/~cjlin/libsvm/.
    [49] C.C. Chang, C.J. Lin, LIBSVM Version 2.8, April 1, 2005, available at http://www.csie.ntu.edu.tw/~cjlin/libsvm/.
    [50] L.A. ZADEH, “FUZZY SETS AS A BASIS FOR A THEORY OF POSSIBILITY,” Fuzzy Sets and System, vol. 1, pp. 3-28, 1978.
    [51] K.S. Barber, “Conflict Detection During Plan Integration for Multi-Agent System,” IEEE Transaction on System, Man and Cybernetics, PART B, vol. 31, no. 4, pp. 616-628, August 2001.
    [52] P. Borne, “Decision Support System for Urban Transportation Networks,” IEEE Transaction on System, Man and Cybernetics, PART C, vol. 33, no. 1, pp. 67-77, February 2003.
    [53] V. Cho, “A COMPARISON OF THREE DIFFERENT APPROACHES TO TOURIST ARRIVAL FORECASTING,” In Proceedings of 2001 ABAS Globalization and Emerging Economies International Conference, 2001.
    [54] K.k. Hung, Y.M. Cheung, L. Xu, “An Extended ASLD Trading System to Enhance Portfolio Management,” IEEE Transactions on Neural Networks, vol. 14, no. 2, pp. 413-425, March 2003.
    [55] ezChart, a free database of Taiwan Stock Exchange Capitalization Weighted (TAIEX) price series, available at http://www.ezchart.com.tw/index.php
    [56] Mutual Fund Performance Evaluation, the Department of Finance, National Taiwan University, available at http://140.112.111.12

    QR CODE