1. NCCU Academic Hub
  2. 學術產出
  3. College of Social Science
  4. Theses
  5. Item

學術產出-Theses

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

  • No doi shows Citation Infomation
題名 利用演化性神經網路預測高頻率時間序列：恆生股價指數的研究
Forecasting High-Frequency Financial Time Series with Evolutionary Neural Trees：The Case of Hang Seng Stock Price Index
作者 王宏碩
Wang, Hung-Shuo
貢獻者 陳樹衡
Cheng, Shu-Heng
王宏碩
Wang, Hung-Shuo
關鍵詞 演化性神經網路
神經樹
加/乘神經樹
生長式遺傳演算法
遺傳程式
Evolutionary Artificial Neural Networks
Neural Trees
Sigma-Pi Neural Trees
Breeder Genetic Algorithm
Genetic Programming
日期 1998
上傳時間 27-Apr-2016 11:12:29 (UTC+8)
摘要 為了瞭解影響演化性神經網路（ENT）預測表現的四項重要的機制：輸入資料性質、訓練樣本大小、網路搜尋密度以及控制模型複雜度，進而找出能使ENT充分發揮效果的組合。在本論文中首先設計ENT在模擬資料上的實驗，探討上述四項機制個別對預測表現的影響，再依照實驗結果的建議，設計能讓ENT發揮功效的組合，並以實際金融高頻率資料：香港恆生指數在一九九八年十二月報酬率為標的，探討模擬資料的結果在實際金融資料需要調整的部份。實驗結果顯示，當輸入資料經過線性過濾後，搭配大樣本訓練、高搜尋強度與適當地模型複雜度控制，會是能讓神經網路提高預測能力的組合。在實際金融資料的實驗當中同時發現，資料中偶而出現特別高或特別低的變化，會對ENT的預測表現有相當程度的影響。
In this thesis, Evolutionary Neural Trees (ENTs) are applied to forecast the artificial data generated by financial and chaos models — iid random, linear process (Auto Regressive-Moving Average；ARMA), nonlinear processes (AutoRegressive Conditional Heteroskedasticity；ARCH, General AutoRegressive Conditional Heteroskedasticity；GARCH, Bilinear), mixed linear and nonlinear process (AR and GARCH). Experiments of the artificial data were conducted to understand the characteristics of ENTs mechanism. – data pre-processing procedures, search intensity, sample size and complexity regularization. From the experiment results of artificial data, the combination of pure linear or nonlinear time series, large sample size, intensive search and simple neural trees are suggested for the parameters setting of ENTs. And for the sake of computational burden, we have a trade-off between search intensity and sample size. Ten experiments are designed for ENTs modeling on the high-frequency stock returns of Heng Sheng stock index on December, 1998, in order to have an efficient combination of the factors of ENTs.
參考文獻 [1]Box, G. E. P. and G. M. Jenking, (1976), “Time Series Analysis: Forecasting and Control” Holded- Day, San Fransisco.
     [2]Bollerslev, T. P. (1986), “Generalized AutoRegressive Conditional Heteroskedasticity” Journal of Economics Vol. 31, pp. 307-327.
     [3]Bowen, J. E. (1994), " A Neural Network Project Roadmap" NeuralVest Journal Vol. 2, No. 5, pp. 7-11.
     [4]Brockett, R. W. (1976), “Volterra Series and Geometric Control Theory” Automatica, Wiley, New York.
     [5]Calderon-Rossell, J.R. and M. Ben-Horim (1982), “The Behavior of Foreign Exchange Rates”, Journal of International Business Studies Vol. 13, pp. 99-111.
     [6]Caldwell, R. B. (1994), “Design of Neural Network- Based Financial Forecasting Systems: Data Selection and Data Processing”, NEUROVE$T JOURNAL Vol. 2 No. 5 pp. 12- 20.
     [7]Chen, S. -H., B. -T. Zhang and H. -S. Wang (1999), “Forecasting High-Frequency Financial Time Series with Evolutionary Neural Trees: The Case of Heng Sheng Stock Index.” Forthcoming in Proceeding of International Conference of Artificial Intelligent.
     [8]Chen, S. -H. and C.- F. Lu (1999), “Would Evolutionary Computation Help in Designs of ANNs in Forecasting Foreign Exchange Rates?” forthcoming in Proceeding of 1999 Congress on Evoltionary Computation, IEEE Press.
     [9] Chu, C. –H. And D. Widjaja (1994), “Neural Network System for Forecasting Method Selection” Decision Support Systems, Vol. 12, pp. 13-24.
     [10]Lu C. -F. (1998), “To Discuss the Random Walk Property of the Foreign Exchange Rate” Master Thesis of National Cheng-Chi University Dept. of Economic.
     [11]Dacorogna, M.M., C.L. Gauvreau, U.A. Muller, R.B. Olsen, and O.V. Pictet (1992), “Short Term Forecasting Models of Foreign Exchange Rates”, Technical Report MMD. 1992-05-12, Olsen & Associates, Zurich.
     [12]Dacorogna, M.M., C.L. Gauvreau, U.A. Muller, R.B. Olsen, and O.V. Pictet (1993), “A Geographical Model for the Daily and weekly Seasonal Volatility in the FX market”, Journal of International Money and Finance, Vol. 12, 413-438.
     [13]Deboeck, G. J. (1994) “Trading on The Edge” Wiley, New York.
     [14]Dickey, D. A. and W. A. Fuller. (1981) “Likelihood Ratio Statistics for Autoregressive Time Series with a Unit Root” Econometrica Vol. 49, pp. 1057-1072.
     [15]Diebold, F.X. (1988), “Empirical Modeling of Exchange Rate Dynamics” Springer-Verlag, New York.
     [16]Dorsey, R. E., J. D. Johnson and W. J. Mayer (1994), “A Genetic Algorithm for the Training of Feedforward Neural Networks,” in J. D. Johnson and A. B. Whinston (eds.), Advances in Artificial Intelligence in Economics, Finance, and Management, Vol. I, JAI Press. pp. 93-111.
     [17]Drost, F. and T.E. Nijman, (1993), “Temporal Aggregation of GARCH Processes”, Econometrica Vol. 61, No. 4, pp. 909-927.
     [18]Dunis, C. (1996), “The Economic Value of Neural Network Systems for Exchange Rate Forecasting”, Neural Network World, Vol. 6, 43-55.
     [19]Engle, R.F. (1982), “Autoregressive Conditional Heteroskedasticity with Estimates of U.K. Inflation”, Econometrica, Vol.50, pp. 987-1008.
     [20]Engle, R.F., T. Ito and W.L. Lin (1990), “Meteor Showers or Heat Waves? Heteroskedastic Intra-daily Volatility in the Foreign Exchange Market”, Econometrica, Vol.58, pp. 525-542.
     [21]Harrald, P. G. and M. Kamstra (1997), “Evolving Artificial Neural Networks to Combine Financial Forecasts,” IEEE Transactions on Evolutionary Computation, Vol. 1, No. 1, pp. 40-52.
     [22]Goodhart, C.A.E. and M. Giugale (1993), “From Hour to Hour in the Foreign Exchange Market”, The Manchester School of Economic and Social Studies Vol. 61, No. 1, pp. 1-34.
     [23]Granger C. W. J. and D. Orr, (1972) “Infinite Variance and Research Strategy in Time Series Analysis.” Journal of the American Statistical Association Vol. 67, pp. 275- 285
     [24] Hoptrof, R. C., J. Bramson, and T. J. Hall (1991), “Forecasting Economic Turning Points with Neural Nets,” Proceeding of International Joint Conference on Neural Nets, Vol. 1, pp.347-352.
     [25]Hsieh D.A. (1988), “The Statistical Properties of Daily Foreign Exchange Rates: 1974-1983”, Journal of International Economics Vol. 24 pp. 129-145.
     [26]Hutchinson, J. M., A. W. Lo, and T. Poggio (1994), “A Nonparametric Approach to Pricing and Hedging Derivative Securities Via Learning Networks,” Journal of Finance, Vol. XLIX, No. 3, pp. 851-889.
     [27]Jang, G.-S. and F. Lai (1994), “Intelligent Trading of an Emerging Markets,” in Deboeck, G. J. (ed.), Trading on the Edge: Neural, Genetic, and Fuzzy Systems for Chaotic Financial Markets, Wiley, New York.
     [28]Judge, G. G., R. C. Hill, W. Griffiths, H. Lütkepohl and T.-C. Lee (1986), “Introduction to the Theory and Practice of Econometrics” Second Edition, Wiley, New York.
     [29]Kamijo, K.-I., and T. Tanigawa (1990), “Stock Price Pattern Recognition: A Recurrent Neural Network Aproach,” Proceedings of the IEEE International Joint Conference on Neural Networks, Vol.1, pp. 2215-2221.
     [30]Kimoto, T., K. Asakawa, M. Yoda, and M. Takeoka (1990), “Stock Market Prediction System with Modular Neural Networks,” Proceedings of the International Joint Conference on Neural Networks, Vol. 1, pp. 1-6.
     [31]Kuan, C.-M. and T. Liu (1995), “Forecasting Exchange Rates Using Feedforward and Recurrent Neural Networks,” Journal of applied Econometrics, Vol. 10, pp. 347-364.
     [32]LeBaron, B. (1992), “Forecast Improvements Using a Volatility Index”, Journal of Applied Econometrics, Vol. 7, 137-149.
     [33]Lee, C. H. and K. C. Park (1992), “Prediction of Monthly Transition of the Composition of Stock Price Index Using Recurrent Back-Propagation,” Artificial Neural Network 2, pp. 1629-1632.
     [34] Liou, R.W. and C.H. Shen (1996), “The Use of High Frequency Data to Improve Macroeconomic Forecast”, International Economic Journal Vol. 10, No. 2, pp. 65-83.
     [35]Mandelbrot, B.B. (1963), “The Variation of Certain Speculative Prices”, Journal of Business, Vol. 36, pp. 394-419.
     [36]Margarita, S. (1991), “Neural Network, Genetic Algorithms and Stock Trading,” Artificial Neural Networks Vol. 1, pp. 1763-1766.
     [37]Moody, J. and L. Wu (1997), “What is the “True Price”?- States Space Models for High Frequency FX DATA,” Proceedings of the Conference on Computational Intelligence for Financial Engineering, IEEE Press.
     [38]Mohler, R. R. (1973), “Bilinear Control Process” Academic Press, New York and London.
     [39]Pictet, O.V., Dacorogna, M.M., Olsen, R.B. and J.R. Ward, (1992), “Real-Time Trading Models for Foreign Exchange Rates”, Neural Network World, Vol. 2, pp. 713-744.
     [40]Priestley, M. B. “Nonlinear and Non-stationary Time Series Analysis.” Academic Press, London.
     [41]Refense, A. N. and C. Alippi (1995), “Histological Image Understanding by Error Backpropagation” Microprocessing and Microprogramming, Vol. 32, No. 3, pp. 437- 446.
     [42]Refense, A. N. (1993), “Constructive Learning and its Application to Currency Exchange Rate Prediction.” In: Turban & Trippi (eds) Neural network Applications in Investment and Finance Servies. Probus Publishing, USA.
     [43]Refense, A. N. (1995), “Neural Networks in the Capital Market” Wiley, New York.
     [44]Ruberti, A., A. Isidori and P. d’Allessandro (1972), “Theory of Bilinear Dynamical Systems.” Springer Verlag, Berlin.
     [45]Sexton, R., I. Johnson and R. Dorsey (1995), “Obtaining a Global Optimum for Neural Networks,” Working Paper, Department of Economics and Finance, University of Mississippi.
     [46]Sietsma, J. and R. F. J. Dow (1991), “Creating Artificial Neural Networks That Generalize” Neural Networks, Vol.4, pp. 67- 79.
     [47]Subba Rao, T. (1981), “On the Theory of Bilinear Time Series Models,” Journal of the Royal Statistical Society, Seres B, Vol. 43, pp. 244- 255.
     [48]Subba Rao, T. and M. M. Grbr (1980), “An Introduction to Bispectral Analysis and Bilinear Time Series Models.” Lecture Notes in Statistics Vol. 24 Springer Verlag, New York.
     [49]Tauchen, G. and M. Pitts (1983), “The Price Variablity-volume Relationship on Speculative Markets”, Econometrica Vol. 51, No. 2, pp. 485-505.
     [50]Tsao, C.-U.(1999), “The Statistical Analysis of GAs- Based Trading Strategies under Dynamic Landscape.” Master Thesis of National Cheng-Chi University. Republic of China, Taiwan.
     [51]VanEyden, R. J. and J. J. L. Cronjè (1994), "Discriminant Analysis Versus Neural Networks in Credit Scoring," NeuralVest Journal Vol. 2, No. 6., pp. 11-15.
     [52] Weigend, A. S., B. A. Huberman and D. E. Rumelhart (1992), “Pridicting Sunspots and Exchange Rates with Connectionist Network,” Nonlinear Modeling and Forecasting, SFI Studies in Science of Complexity 7 pp. 395-342.
     [53]White, H. (1988), “Economic Prediction Using Neural Networks: The Case of IBM Daily Stock Returns,” in Proceedings of the IEEE International Conference on Neural Networks, Vol. II, pp. 451-458.
     [54]Wu, B. and N. Shih (1992), “On the Identification Problem for bilinear Time Series Models,” Journal of Computational Statistics Simulation. Vol. 43, pp. 129- 161.
     [55]Yao, X. (1993), “A Review of Evolutionary Artificial Neural Networks,” International Journal of Intelligent Systems, Vol. 8, No. 4, pp. 539-567.
     [56]Yao, X. (1993), “Evolutionary Artificial Neural Networks,” International Journal of Neural Systems, Vol. 4, No. 3, pp. 203-222.
     [57] Yao, X. and Y. Liu (1997), “A New Evolutionary System for Evolving Artificial Neural Networks,” IEEE Transactions on Neural Networks, Vol. 8, No. 3, pp. 694-713.
     [58]Zhang B.-T. and H. Mülenbein (1995), “Balancing accuracy and parsimony in genetic programming.” Evolutionary Computation, Vol. 3, pp.17-38, 1995.
     [59]Zhang B.-T., P. Ohm, and H. Mülenbein (1997), “Evolutionary induction of sparse neural trees.” Evolutionary Computation, Vol.5, No.2, pp. 213-236.
     [60]Zhou, B.(1996), “High-frequency data and volatility in Foreign-exchange Rates”, Journal of Business and Economic Statistics Vol. 14, No.1, 45-52.
描述 碩士
國立政治大學
經濟學系
86258014
資料來源 http://thesis.lib.nccu.edu.tw/record/#B2002001629
資料類型 thesis
dc.contributor.advisor 陳樹衡zh_TW
dc.contributor.advisor Cheng, Shu-Hengen_US
dc.contributor.author (Authors) 王宏碩zh_TW
dc.contributor.author (Authors) Wang, Hung-Shuoen_US
dc.creator (作者) 王宏碩zh_TW
dc.creator (作者) Wang, Hung-Shuoen_US
dc.date (日期) 1998en_US
dc.date.accessioned 27-Apr-2016 11:12:29 (UTC+8)-
dc.date.available 27-Apr-2016 11:12:29 (UTC+8)-
dc.date.issued (上傳時間) 27-Apr-2016 11:12:29 (UTC+8)-
dc.identifier (Other Identifiers) B2002001629en_US
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/86204-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 經濟學系zh_TW
dc.description (描述) 86258014zh_TW
dc.description.abstract (摘要) 為了瞭解影響演化性神經網路（ENT）預測表現的四項重要的機制：輸入資料性質、訓練樣本大小、網路搜尋密度以及控制模型複雜度，進而找出能使ENT充分發揮效果的組合。在本論文中首先設計ENT在模擬資料上的實驗，探討上述四項機制個別對預測表現的影響，再依照實驗結果的建議，設計能讓ENT發揮功效的組合，並以實際金融高頻率資料：香港恆生指數在一九九八年十二月報酬率為標的，探討模擬資料的結果在實際金融資料需要調整的部份。實驗結果顯示，當輸入資料經過線性過濾後，搭配大樣本訓練、高搜尋強度與適當地模型複雜度控制，會是能讓神經網路提高預測能力的組合。在實際金融資料的實驗當中同時發現，資料中偶而出現特別高或特別低的變化，會對ENT的預測表現有相當程度的影響。zh_TW
dc.description.abstract (摘要) In this thesis, Evolutionary Neural Trees (ENTs) are applied to forecast the artificial data generated by financial and chaos models — iid random, linear process (Auto Regressive-Moving Average；ARMA), nonlinear processes (AutoRegressive Conditional Heteroskedasticity；ARCH, General AutoRegressive Conditional Heteroskedasticity；GARCH, Bilinear), mixed linear and nonlinear process (AR and GARCH). Experiments of the artificial data were conducted to understand the characteristics of ENTs mechanism. – data pre-processing procedures, search intensity, sample size and complexity regularization. From the experiment results of artificial data, the combination of pure linear or nonlinear time series, large sample size, intensive search and simple neural trees are suggested for the parameters setting of ENTs. And for the sake of computational burden, we have a trade-off between search intensity and sample size. Ten experiments are designed for ENTs modeling on the high-frequency stock returns of Heng Sheng stock index on December, 1998, in order to have an efficient combination of the factors of ENTs.en_US
dc.description.tableofcontents 1Introduction and Brief Review 1
     1.1 Introduction of Artificial Neural Networks (ANNs) and Its Design Steps.........1
     1.1.1 The Biological Foundation of Neural Networks.........2
     1.1.2 The Design Steps of Artificial Neural Networks.........2
     1.2 Literature Review.........3
     1.2.1 Methods for Optimal Network Design.........4
     1.2.2 Description of Problems Met in Design Process.........6
     1.3 Evolutionary Artificial Neural Networks.........7
     1.3.1 The Evolution of Connection Weights.........8
     1.3.2 The Evolution of Architecture.........9
     1.3.3 The Evolution of Learning Rules.........10
     1.3.4 The Level to Develop the EANN.........11
     2 Introduction of Evolutionary Neural Trees 12
     2.1 Neural Trees.........12
     2.2 Evolving Neural Trees.........16
     3 Experiments on Artificial Data 19
     3.1 Simulation Designs and Analysis.........20
     3.1.1 IID Random......... 20
     3.1.2 ARMA.........20
     3.1.3 ARCH.........21
     3.1.4 GARCH.........21
     3.1.5 BiLinear.........22
     3.1.6 Chaos Series.........23
     3.2 Monte Carlo Simulation.........23
     3.3 Parameters Setting in ENTs.........24
     3.3.1 Data Pre-Processing.........24
     3.3.2 Search Intensity.........25
     3.3.3 Sample Size.........26
     3.3.4 Parsimony Pressure.........27
     3.4 Experimental Results.........28
     3.4.1 Comparison Criterion.........28
     3.4.2 Data Pre-processing.........29
     3.4.3 Search Intensity and Training Data Set Size.........34
     3.4.4 Parsimony Pressure.........35
     3.5 Summary.........36
     4 Financial Time Series Analysis 37
     4.1 Data Description.........37
     4.1.1 High-frequency Data.........37
     4.1.2 The Statistical Properties of High-frequency Data.........38
     4.1.3 The Evolution of data Frequency.........40
     4.2 Data Pre-processing.........41
     4.2.1 Basic Economic Properties of PRICE Series.........42
     4.2.2 Basic Economic Properties of RETURN Series.........44
     4.2.3 Linear and Nonlinear Filtering.........44
     4.2.4 Summary of Data Filtering.........47
     4.3 Parameters Setting of Financial Data.........49
     4.3.1 Number of Input / Output Variables.........49
     4.3.2 Training / Test Data Set Size.........50
     4.3.3 Transfer Functions.........50
     4.3.4 The Fitness Function.........51
     4.3.5 Linear and Nonlinear Enlarge.........51
     4.3.6 Other Heuristic.........52
     4.4 The Arrangement of Experiments.........53
     4.4.1 Designs of Data Pre-Processing.........53
     4.4.2 Designs of Large/ Small Training Sample Size and Appropriate Parsimonious Pressure.........55
     5 Conclusions 58
     References 60		zh_TW
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#B2002001629en_US
dc.subject (關鍵詞) 演化性神經網路zh_TW
dc.subject (關鍵詞) 神經樹zh_TW
dc.subject (關鍵詞) 加/乘神經樹zh_TW
dc.subject (關鍵詞) 生長式遺傳演算法zh_TW
dc.subject (關鍵詞) 遺傳程式zh_TW
dc.subject (關鍵詞) Evolutionary Artificial Neural Networksen_US
dc.subject (關鍵詞) Neural Treesen_US
dc.subject (關鍵詞) Sigma-Pi Neural Treesen_US
dc.subject (關鍵詞) Breeder Genetic Algorithmen_US
dc.subject (關鍵詞) Genetic Programmingen_US
dc.title (題名) 利用演化性神經網路預測高頻率時間序列：恆生股價指數的研究zh_TW
dc.title (題名) Forecasting High-Frequency Financial Time Series with Evolutionary Neural Trees：The Case of Hang Seng Stock Price Indexen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) [1]Box, G. E. P. and G. M. Jenking, (1976), “Time Series Analysis: Forecasting and Control” Holded- Day, San Fransisco.
     [2]Bollerslev, T. P. (1986), “Generalized AutoRegressive Conditional Heteroskedasticity” Journal of Economics Vol. 31, pp. 307-327.
     [3]Bowen, J. E. (1994), " A Neural Network Project Roadmap" NeuralVest Journal Vol. 2, No. 5, pp. 7-11.
     [4]Brockett, R. W. (1976), “Volterra Series and Geometric Control Theory” Automatica, Wiley, New York.
     [5]Calderon-Rossell, J.R. and M. Ben-Horim (1982), “The Behavior of Foreign Exchange Rates”, Journal of International Business Studies Vol. 13, pp. 99-111.
     [6]Caldwell, R. B. (1994), “Design of Neural Network- Based Financial Forecasting Systems: Data Selection and Data Processing”, NEUROVE$T JOURNAL Vol. 2 No. 5 pp. 12- 20.
     [7]Chen, S. -H., B. -T. Zhang and H. -S. Wang (1999), “Forecasting High-Frequency Financial Time Series with Evolutionary Neural Trees: The Case of Heng Sheng Stock Index.” Forthcoming in Proceeding of International Conference of Artificial Intelligent.
     [8]Chen, S. -H. and C.- F. Lu (1999), “Would Evolutionary Computation Help in Designs of ANNs in Forecasting Foreign Exchange Rates?” forthcoming in Proceeding of 1999 Congress on Evoltionary Computation, IEEE Press.
     [9] Chu, C. –H. And D. Widjaja (1994), “Neural Network System for Forecasting Method Selection” Decision Support Systems, Vol. 12, pp. 13-24.
     [10]Lu C. -F. (1998), “To Discuss the Random Walk Property of the Foreign Exchange Rate” Master Thesis of National Cheng-Chi University Dept. of Economic.
     [11]Dacorogna, M.M., C.L. Gauvreau, U.A. Muller, R.B. Olsen, and O.V. Pictet (1992), “Short Term Forecasting Models of Foreign Exchange Rates”, Technical Report MMD. 1992-05-12, Olsen & Associates, Zurich.
     [12]Dacorogna, M.M., C.L. Gauvreau, U.A. Muller, R.B. Olsen, and O.V. Pictet (1993), “A Geographical Model for the Daily and weekly Seasonal Volatility in the FX market”, Journal of International Money and Finance, Vol. 12, 413-438.
     [13]Deboeck, G. J. (1994) “Trading on The Edge” Wiley, New York.
     [14]Dickey, D. A. and W. A. Fuller. (1981) “Likelihood Ratio Statistics for Autoregressive Time Series with a Unit Root” Econometrica Vol. 49, pp. 1057-1072.
     [15]Diebold, F.X. (1988), “Empirical Modeling of Exchange Rate Dynamics” Springer-Verlag, New York.
     [16]Dorsey, R. E., J. D. Johnson and W. J. Mayer (1994), “A Genetic Algorithm for the Training of Feedforward Neural Networks,” in J. D. Johnson and A. B. Whinston (eds.), Advances in Artificial Intelligence in Economics, Finance, and Management, Vol. I, JAI Press. pp. 93-111.
     [17]Drost, F. and T.E. Nijman, (1993), “Temporal Aggregation of GARCH Processes”, Econometrica Vol. 61, No. 4, pp. 909-927.
     [18]Dunis, C. (1996), “The Economic Value of Neural Network Systems for Exchange Rate Forecasting”, Neural Network World, Vol. 6, 43-55.
     [19]Engle, R.F. (1982), “Autoregressive Conditional Heteroskedasticity with Estimates of U.K. Inflation”, Econometrica, Vol.50, pp. 987-1008.
     [20]Engle, R.F., T. Ito and W.L. Lin (1990), “Meteor Showers or Heat Waves? Heteroskedastic Intra-daily Volatility in the Foreign Exchange Market”, Econometrica, Vol.58, pp. 525-542.
     [21]Harrald, P. G. and M. Kamstra (1997), “Evolving Artificial Neural Networks to Combine Financial Forecasts,” IEEE Transactions on Evolutionary Computation, Vol. 1, No. 1, pp. 40-52.
     [22]Goodhart, C.A.E. and M. Giugale (1993), “From Hour to Hour in the Foreign Exchange Market”, The Manchester School of Economic and Social Studies Vol. 61, No. 1, pp. 1-34.
     [23]Granger C. W. J. and D. Orr, (1972) “Infinite Variance and Research Strategy in Time Series Analysis.” Journal of the American Statistical Association Vol. 67, pp. 275- 285
     [24] Hoptrof, R. C., J. Bramson, and T. J. Hall (1991), “Forecasting Economic Turning Points with Neural Nets,” Proceeding of International Joint Conference on Neural Nets, Vol. 1, pp.347-352.
     [25]Hsieh D.A. (1988), “The Statistical Properties of Daily Foreign Exchange Rates: 1974-1983”, Journal of International Economics Vol. 24 pp. 129-145.
     [26]Hutchinson, J. M., A. W. Lo, and T. Poggio (1994), “A Nonparametric Approach to Pricing and Hedging Derivative Securities Via Learning Networks,” Journal of Finance, Vol. XLIX, No. 3, pp. 851-889.
     [27]Jang, G.-S. and F. Lai (1994), “Intelligent Trading of an Emerging Markets,” in Deboeck, G. J. (ed.), Trading on the Edge: Neural, Genetic, and Fuzzy Systems for Chaotic Financial Markets, Wiley, New York.
     [28]Judge, G. G., R. C. Hill, W. Griffiths, H. Lütkepohl and T.-C. Lee (1986), “Introduction to the Theory and Practice of Econometrics” Second Edition, Wiley, New York.
     [29]Kamijo, K.-I., and T. Tanigawa (1990), “Stock Price Pattern Recognition: A Recurrent Neural Network Aproach,” Proceedings of the IEEE International Joint Conference on Neural Networks, Vol.1, pp. 2215-2221.
     [30]Kimoto, T., K. Asakawa, M. Yoda, and M. Takeoka (1990), “Stock Market Prediction System with Modular Neural Networks,” Proceedings of the International Joint Conference on Neural Networks, Vol. 1, pp. 1-6.
     [31]Kuan, C.-M. and T. Liu (1995), “Forecasting Exchange Rates Using Feedforward and Recurrent Neural Networks,” Journal of applied Econometrics, Vol. 10, pp. 347-364.
     [32]LeBaron, B. (1992), “Forecast Improvements Using a Volatility Index”, Journal of Applied Econometrics, Vol. 7, 137-149.
     [33]Lee, C. H. and K. C. Park (1992), “Prediction of Monthly Transition of the Composition of Stock Price Index Using Recurrent Back-Propagation,” Artificial Neural Network 2, pp. 1629-1632.
     [34] Liou, R.W. and C.H. Shen (1996), “The Use of High Frequency Data to Improve Macroeconomic Forecast”, International Economic Journal Vol. 10, No. 2, pp. 65-83.
     [35]Mandelbrot, B.B. (1963), “The Variation of Certain Speculative Prices”, Journal of Business, Vol. 36, pp. 394-419.
     [36]Margarita, S. (1991), “Neural Network, Genetic Algorithms and Stock Trading,” Artificial Neural Networks Vol. 1, pp. 1763-1766.
     [37]Moody, J. and L. Wu (1997), “What is the “True Price”?- States Space Models for High Frequency FX DATA,” Proceedings of the Conference on Computational Intelligence for Financial Engineering, IEEE Press.
     [38]Mohler, R. R. (1973), “Bilinear Control Process” Academic Press, New York and London.
     [39]Pictet, O.V., Dacorogna, M.M., Olsen, R.B. and J.R. Ward, (1992), “Real-Time Trading Models for Foreign Exchange Rates”, Neural Network World, Vol. 2, pp. 713-744.
     [40]Priestley, M. B. “Nonlinear and Non-stationary Time Series Analysis.” Academic Press, London.
     [41]Refense, A. N. and C. Alippi (1995), “Histological Image Understanding by Error Backpropagation” Microprocessing and Microprogramming, Vol. 32, No. 3, pp. 437- 446.
     [42]Refense, A. N. (1993), “Constructive Learning and its Application to Currency Exchange Rate Prediction.” In: Turban & Trippi (eds) Neural network Applications in Investment and Finance Servies. Probus Publishing, USA.
     [43]Refense, A. N. (1995), “Neural Networks in the Capital Market” Wiley, New York.
     [44]Ruberti, A., A. Isidori and P. d’Allessandro (1972), “Theory of Bilinear Dynamical Systems.” Springer Verlag, Berlin.
     [45]Sexton, R., I. Johnson and R. Dorsey (1995), “Obtaining a Global Optimum for Neural Networks,” Working Paper, Department of Economics and Finance, University of Mississippi.
     [46]Sietsma, J. and R. F. J. Dow (1991), “Creating Artificial Neural Networks That Generalize” Neural Networks, Vol.4, pp. 67- 79.
     [47]Subba Rao, T. (1981), “On the Theory of Bilinear Time Series Models,” Journal of the Royal Statistical Society, Seres B, Vol. 43, pp. 244- 255.
     [48]Subba Rao, T. and M. M. Grbr (1980), “An Introduction to Bispectral Analysis and Bilinear Time Series Models.” Lecture Notes in Statistics Vol. 24 Springer Verlag, New York.
     [49]Tauchen, G. and M. Pitts (1983), “The Price Variablity-volume Relationship on Speculative Markets”, Econometrica Vol. 51, No. 2, pp. 485-505.
     [50]Tsao, C.-U.(1999), “The Statistical Analysis of GAs- Based Trading Strategies under Dynamic Landscape.” Master Thesis of National Cheng-Chi University. Republic of China, Taiwan.
     [51]VanEyden, R. J. and J. J. L. Cronjè (1994), "Discriminant Analysis Versus Neural Networks in Credit Scoring," NeuralVest Journal Vol. 2, No. 6., pp. 11-15.
     [52] Weigend, A. S., B. A. Huberman and D. E. Rumelhart (1992), “Pridicting Sunspots and Exchange Rates with Connectionist Network,” Nonlinear Modeling and Forecasting, SFI Studies in Science of Complexity 7 pp. 395-342.
     [53]White, H. (1988), “Economic Prediction Using Neural Networks: The Case of IBM Daily Stock Returns,” in Proceedings of the IEEE International Conference on Neural Networks, Vol. II, pp. 451-458.
     [54]Wu, B. and N. Shih (1992), “On the Identification Problem for bilinear Time Series Models,” Journal of Computational Statistics Simulation. Vol. 43, pp. 129- 161.
     [55]Yao, X. (1993), “A Review of Evolutionary Artificial Neural Networks,” International Journal of Intelligent Systems, Vol. 8, No. 4, pp. 539-567.
     [56]Yao, X. (1993), “Evolutionary Artificial Neural Networks,” International Journal of Neural Systems, Vol. 4, No. 3, pp. 203-222.
     [57] Yao, X. and Y. Liu (1997), “A New Evolutionary System for Evolving Artificial Neural Networks,” IEEE Transactions on Neural Networks, Vol. 8, No. 3, pp. 694-713.
     [58]Zhang B.-T. and H. Mülenbein (1995), “Balancing accuracy and parsimony in genetic programming.” Evolutionary Computation, Vol. 3, pp.17-38, 1995.
     [59]Zhang B.-T., P. Ohm, and H. Mülenbein (1997), “Evolutionary induction of sparse neural trees.” Evolutionary Computation, Vol.5, No.2, pp. 213-236.
     [60]Zhou, B.(1996), “High-frequency data and volatility in Foreign-exchange Rates”, Journal of Business and Economic Statistics Vol. 14, No.1, 45-52.		zh_TW