臺灣博碩士論文加值系統

時間序列的預測是困難的，尤其是證券市場指數的波動有著人為、經濟、政治、技術面和產業面等因素的影響，所以股價走勢的預測是更為不易的。現行預測的機制以類神經網路效能較佳，他們是非線性可調適性的模式，不須預先指定特別的型式就有能力去估計複雜的關係。自我組織特徵映射圖(Self-Organizing Map, SOM)是一個非監督式的類神經經網路，自我組織特徵映射圖能夠將高維度的資料藉由映射的方式對映至二維或一維的座標空間上，以利資料分群之進行。GM(1,1)是一種灰預測的基本模式，能在資訊不完整及不確定下具有系統預測的能力。
本學位論文提出一系列整合的時間序列預測機制，除了灰色自我組織特徵映射圖(Grey SOM based on GRG, GSOMGRG)，灰色傅立葉自我組織特徵映射圖(Grey Fourier SOM based on GRG, GFSOMGRG)外，另建立二階段灰色自我組織特徵映射圖模型(Two-stage GSOMGRG) 以及二階段灰色傅立葉自我組織特徵映射圖模型(Two-stage GFSOMGRG)，分別探討各模型在時間序列資料中估計和預測績效的表現。它們將傳統自我組織特徵映射圖與灰色理論的灰色關聯度(Grey Relational Grade, GRG)結合成一種新的聚類機制---灰關聯自我組織特徵映射圖 (SOM based on GRG, SOMGRG)，把一段時間序列資料視為一個幾何圖像，使用SOMGRG將圖像聚類，加上時間序列資料的前後處理機制，使得預測值的精確度更為提昇。此預測機制首先將時間序列進行GM(1,1)預測，再將其差分化的資料視為圖像，以灰關聯在自我組織特徵映射圖架構上進行圖像的聚類，之後將同類別資料的預測值進行修正，以得到更佳的預測值。在時間序列進行GM(1,1)預測過程中，GFSOMGRG增加了傅立葉殘差修正以增加GM(1,1)預測值準確度。在SOMGRG將圖像聚類時，two-stage 的機制進行二次聚類，以增進SOMGRG聚類的精確度。實驗數據中顯示Two-stage GFSOMGRG 比起其它模型預測能力更佳，進而能幫助投資者預測未來股票價格指數和掌握獲利的機會。

Time series prediction is a difficult task. The prediction of stock price trends is particularly difficult because the volatility of the stock market index is affected by human, economic, political, technical and industrial factors. Among the currently used prediction mechanisms, neural networks show the best performance. Neural networks are nonlinear adaptive models and have the ability to approximate complex relations which may not have a prespecified form. A self-organizing map (SOM) is an unsupervised neural network that uses the similarity of high-dimensional data in a two-dimensional or one-dimensional coordinate space to facilitate data classification. GM(1,1) is a basic model for grey prediction and is capable of providing system predictions under the constraints of uncertainty and imperfect information.
This paper presents a series of integrated time series prediction mechanisms. In addition to Grey SOM based on GRG (GSOMGRG) and Grey Fourier SOM based on GRG (GFSOMGRG), we explain the concepts of Two-stage GSOMGRG and Two-stage GFSOMGRG, which respectively predict and estimate the performance of models of time series data. The traditional SOM and Grey Relational Grade (GRG) of grey theory are combined into a new clustering mechanism, SOMGRG. A period of time series data is regarded as a pattern, and patterns are clustered with SOMGRG, together with the pre- and post-processing mechanisms of time series data, so that the accuracy of the predicted values is further enhanced. This prediction mechanism first uses GM(1,1) to predict the time series, and then the differencing data is regarded as forming patterns. The patterns are then clustered with GRG into a SOM structure. Then, the predicted values of the same type of data are modified to obtain better values. In the GM(1,1) predicting process, GFSOMGRG uses Fourier residual correction to increase the GM (1,1) prediction accuracy. For developing SOMGRG clustering patterns, a two-stage mechanism performs clustering twice in order to improve the accuracy of SOMGRG clustering. The experimental results show that Two-stage GFSOMGRG has better forecasting ability compared to other models and can help investors predict future stock price indices and grasp profit-making opportunities.

論 文 摘 要 I
Abstract II
誌 謝 III
Contents IV
Glossary of Symbols VI
List of Figures VII
List of Tables VIII
Chapter 1 Introduction 1
1.1 Motivation 6
1.2 Purpose 9
1.3 Research Problem 11
1.4 Organization 11
Chapter 2 Review of Related Methodologies 13
2.1 Clustering 13
2.1.1 Self-Organizing Map (SOM) 15
2.2 Grey Theory 18
2.2.1 Grey Relational Analysis 20
2.2.2 GM(1,1) 25
2.3 Grey Fourier (GF) 27
2.4 Technical Index 28
2.4.1 KD 29
2.4.2 Relative Strength Index (RSI) 30
Chapter 3 Prediction Models 32
3.1 Grey SOM based on GRG (GSOMGRG) 33
3.2 Grey Fourier SOM based on GRG (GFSOMGRG) 38
3.2.1 Grey Fourier.. 38
3.2.2 GFSOMGRG 39
3.3 Two-stage Grey SOM based on GRG (GSOMGRG) 41
3.4 Two-stage Grey Fourier SOM based on GRG (GFSOMGRG) 44
Chapter 4 An Application of GSOMGRG and GFSOMGRG to the Financial Prediction 47
4.1 Experiments 47
4.2 Comparative Analysis 48
4.2.1 Selection of GRG Definitions.. 48
4.2.2 Comparison of SOMGRG Clustering Efficiency 48
4.2.3 Comparison of GSOMGRG Prediction Efficiency.. 49
4.2.4 Comparison GSOMGRG,GFSOMGRG, Two-stage GSOMGRG and Two-stage GFSOMGRG Prediction Efficiency 51
Chapter 5 Conclusions and Future Work 64
5.1 Conclusions 64
5.2 Future Work 65
References 66
作者簡介 73

Reference
[1]F. Chen, Y.H. Chen, & J.Z. Zhang, “Stock index modeling using IP based Gene Expression Programming.”, Computer Engineering and Applications. 45(26), 227-229(2007).
[2]T. Wabgm , “Predicting stock price using fuzzy grey prediction ystem “, Expert System with Applications . 22, 33-39.
[3]B.N. Huang, “Do Asian Stock Market Price Follow Random Walks? Evidence from the Variance Ratio Test’, Applied Financial Economics, 5, 251-256 (1970).
[4]E.F. Fama, and K.R. Frence, “Permanent and temporary Components of Stock Price”, Journal of Political Economy, 96,246-274(1988).
[5]E.F. Fama, “Efficient Capital Markets: A Review of Theory and Works,” Journal of Finance, vol.25, May, pp.381-417 (1970).
[6]E.F. Fama, and M.E. Blume, “Filter Rules and Stock market Trading Profits”, Journal of Business, Vol.39, pp.226-241(1966).
[7]E.F. Fama, “The Behavior of Stock market Prices”, Journal of Business, Vol.33, January, pp.34-105(1965).
[8]M. A. Johnson, “The Random Walk and Beyond:An Inside Guide to the Stock Market”, JohnWiley & Sons, New York (1998).
[9]J. W. Hall, “Adaptive selection of U.S. stock with neural nets,” In: GJ Deboeck (Eds.),Trading on the edge: neural, genetic, and fuzzy systems for chaotic financial markets, Wiley, New York (1994).
[10]S. Yaser, A. F. Atiya, “Introduction to financial forecasting,” Applied Intelligence, Vol. 6,pp.205-13 (1996).
[11]F. E. H. Tay, L. Cao, “Application of support vector machines in financial time series forecasting,” Omega, Vol. 29, No. 4,pp.309-317 (2001).
[12]陳寬裕”結合遺傳演算法與支援向量迴歸” 計量管理期刊Vol. 3, No. 1, page 1~18 (2006).
[13]Weihong Wang, Shuangshuang Nie, “The Performance of Several Combining Forecasts for Stock Index”, International Seminar on Future Information Technology and Management Engineering, IEEE, pp. 450-455 (2008).
[14]W.A. Brock, & A.W. Kleidon, “Periodic market closure and trading volume: a model of intraday bids and asks” Journal of Economic Dynamics and Control. 16 451-489 (1992).
[15]K. G.. Balachandher, M.N. Fauzias & M.M. Lai, “An examination of the random walk model and technique trading rules in the Malaysian stock market”, Quarterly Journal of Business & Economics . 41. 81-104 (2002).
[16]M. Aiken, & M. Bsta, “Forecasting market trends with neural networks”, Information Systems Management, Vol. 16, no. 4, pp. 42-48 (1999).
[17]Q. Cao, K.B. Leggio, & M.J. Schniederjans, “A comparison between Fama and Frech’s model and artificial neural networks in predicting the Chinese stock market”, Computers & Operations Research, Vol. 32, pp. 2499-2512 (2005).
[18]R.J. Kuo, C.H. Chen, & Y.C. Hwang, “A 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, pp. 21-45 (2001).
[19]Y.K. Kwon, & B.R. Moon, “A hybrid neurogenetic approach for stock forecasting”, IEEE Transactions on Neural Networks, Vol. 18, No. 3, May, pp. 851-864 (2007).
[20]K.H. Huarng, & Tiffany H.K. Yu, & T.T. Kao , “Analyzing structural changes using clustering techniques”, International Journal of Innovative Computing, Information and Control, Vol. 4, No. 5, May, pp. 1195-1201 (2008).
[21]A. Abraham, B. Nath, & P.K. Mohanthi, “Hybrid intelligent systems for stock market analysis, in V. N. Alexandrov et al. (eds.)”, Computational science, Springer-Verlag, San Francisco, C.A., pp. 337-45 (2001).
[22]Y, Romahi, Y. & Q. Shen, “Dynamic financial forecasting with automatically induced fuzzy associations”, Proceedings of the 9th international conference on fuzzy systems, pp. 493-98 (2000).
[23]Jr., R.J. Bauer, “Genetic algorithms and investment strategies”, Wiley, New York( 1994).
[24]Ra, M. D., Hassan, U. & B. N. M. Kirley, , “A fusion model of HMM, ANN and GA for stock market forecasting”, Expert Systems with Applications, Vol. 33, pp. 171-80 (2007).
[25]Xiaoming Pan, Jiansheng Wu. “Study on the Stock Market Prediction Model of Neural Ensemble Based on Genetic Algorithms” , Journal of Guangxi Teachers Education University (Natural Science Edition), 24(1):77-84 (2007).
[26]Y.CT. Raymond, “An application of the ARIMA model to real estate prices in Hong Kong”, Journal of Property Finance, Vol. 8, No. 2, pp. 52-163 (1997).
[27]M. Qi, & GP. Zhang, “Trend time-series modeling and forecasting with neural networks”, IEEE Transactions on Neural Network Vol. 19 ,No.5 ,May (2008).
[28]Ni and C. Zhang, “Mining Better Technical Trading Strategies with Genetic Algorithm”, Proc. Of IEEE International Workshop on Integrating AI and Data Mining, Hobart, Australia, pp.26-33 (2006).
[29]F. R. Fernando, G. M. Christian, and S. R. Simon, “Optimization of Technical Rules by Genetic Algorithms: Evidence from the Madrid Stock Market”, Applied Financial Economics, Vol. 15, pp.773-775 (2005)
[30]Asif Ullah Khan, T. K. Bandopadhyaya, Sudhir Sharma.” SOM based Stock Index Performs Better than NSE-50 Index”, Journal Theoretical and Applied Information Technology , pp. 802 (2005).
[31]A. Sfetsos and C. Siriopoulos. “A hybrid clustering scheme for time series forecasting”, In Proceedings of the 8th International Conference of Society for Computational Economics, pages 1–11 (2002).
[32]E. S. Cheng, S. Cheng & B. Mulgew, “Gradient radial basis function network for nonlinear and nonstationary time series prediction,” IEEE transactions on NeuralNetworks, Vol. 7, No. 1, pp.190-194 (1996).
[33]W. Kaminski, P. Strumillo, “Kernel ortho normalizationin radial basis function neural networks,” IEEE Transactions on Neural Networks, Vol. 8, No. 5, pp.1177-1183 (1997).
[34]S. Haykin, “Neural networks: a comprehensive foundation”, Prentice Hall, Englewood Cliffs,NJ (1999).
[35]I. Kastra, S. B. Milton, “Forecasting future strading volume using neural networks,” The Journal of Futures Markets, Vol. 15, No. 8,pp.853-970 (1995).
[36]W. C. Chiang, T. L. Urban & G. Baildridge, “Aneural network approach to mutual fund netasset value forecasting,” Omega, Vol. 24, No. 2,pp.205-219 (1996).
[37]A.P. Azcarraga, T.N. Yap., Jr. J. Tan. And T.S. china, “Evaluating Keyword Selection Methods for SEBSOM Text Archives:”, IEEE Trans. On Knowledge and Data Engineering, Vol. 16(3), pp. 380-383 (2004).
[38]Nicole Powell, Simon Y. Foo, and Mark Weatherspoon,” Supervised and Unsupervised Methods for Stock Trend Forecasting”, 40th Southeastern Symposium on System Theory MC2.2University of New Orleans New Orleans, LA, USA, March 16-18 (2008).
[39]J.A. Michael, L. Gordon , “Data Mining Techniques For marketing Sales and Customer Support”, John Willey & Sons, (1996).
[40]Ye, Qiang, Bing Liang, and Yijun Li. Amnestic “Neural Network for Classification: Application on Stock Trend Prediction.” IEEE (2005).
[41]G.A. Barreto, & A. F. R. Araujo, “Identification and control of dynamical systems using the self-organizing map”, IEEE Transactions on Neural Networks, Vol. 15, No. 5, September, pp. 1244-59 (2004).
[42]C. H. Chang, P. Xu, R. Xiao, & T. Srikanthan, , “New adaptive color quantization method based on self-organizing maps”, IEEE Transactions on Neural Networks, Vol. 16, No. 1, January, pp. 237-49 (2005).
[43]L. Yun, & K. Uchimura, ,” Using self-organizing map for road network extraction from IKONOS imagery”, International Journal of Innovative Computing, Information and Control, Vol. 3, No. 3, June, pp.641-656 (2007).
[44]X. Zhang, X. Li, & X. Chen, “Application of grey modeling method to fitting and forecasting wear trend of marine diesel engines”, Teratology International, Vol. 36, pp. 217-256 (2003).
[45]L. Y. Liu, “Research on the affection of enterprise combinations to the managing performance of the acquiring company—application of the method of the grey correlation analysis”, Postgraduate thesis, Enterprise Management Institute of National Chung Cheng University, Taiwan (2004).
[46]S. M. Chen, “Forecasting enrollments based on high-order fuzzy time series”, Cybernetics and Systems: An International Journal, Vol. 33, pp. l 1-16 (2002).
[47]H. Guterman, , A. Cohen, & I. Laptidot, “Unsupervised speaker recognition based on competition between self-organizing maps”, IEEE Transactions on Neural Networks, Vol. 13, No. 4, July, pp. 877-87 (2002).
[48]M. C. Su and H. C. Chang, “A new model of self-organizing neural networks and its application in data projection,” IEEE Trans. On Neural Networks, 12, No. 1, pp. 153-158, January (2001).
[49]Yu-Chia Hsu , An-Pin Chen, “Clustering Time Series by SOM for the optimal Hedge Ratio Estimation”, Third 2008 International Conference on Convergence and Hybrid Information Technology, IEEE,pp.1164-1169 (2008).
[50]A. W. Lo, & A. C. MacKinglay, “Stock market prices do not follow random walks: Evidence from a simple specification test”, Rev. Financial Studies, Vol. 1, pp. 41-66 (1988).
[51]C. C. Hsu, ”Generalizing self-organizing map for categorical data”, IEEE Transactions on Neural Networks, Vol. 17, No. 2, March, pp. 294-304 (2006).
[52]J. Han, and M. Kamber, “Data mining: Concepts and Techniques.” San Francisco: Morgan Kaufmann Publisher (2001).
[53]E. Martin, H. Kriegel, J. Sander, and X. Xu, “A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise.” ,Proc. of KDD96: pp. 226-231 (1996).
[54]W. Wang, J. Yang, and R/\. Muntz, “STING: A Statistical Information Grid Approach to Spatial Data Mining.” Proc. of the 23th VLDB Conference, pp. 186-195 (1997) .
[55]R. Agrawal, J. Gehrke, D. Gunopulos, and P. Raghavan, , “Automatic Subspace Clustering of High Dimensional Data for Data Mining Applications.”, Proc. of the ACM SIGMOD Conference on Management of Data, pp. 94-104 (1998).
[56]T. Kohonen, “Self-organized formation of topologically correct feature maps”, Biological Cybernetics, Vol. 66, pp. 59-69 (1982).
[57]T Kohonen, “Self-organized and associate memory”, Springer-Verlag, London (1984).
[58]R.J. Kuo, and K.C. Xue, “Fuzzy neural networks with application to sales forecasting”, Fuzzy sets and Systems, 118(1), pp.21-45 (2001).
[59]K.K> Li, K.K., G.J. Chen , T.S. Chung, H.B. Sun and G.Q. Tang, “Application of an innovative combined forecasting method in power system load forecasting”, Electric Power Systems Research, pp.131-137 (2001).
[60]M.C, Mederos, and A. Veiga, “A hybrid linear-neural model for time series forecasting”, IEEE Transactions on Neural Networks, 11(6) , pp.1402-1412 (2000).
[61]H. Mori, and A. Yuihara, “Deterministic annealing clustering for Ann-Based short-term load forecasting”, IEEE Transactions on Power Systems, 16(3), pp.545-551 (2001).
[62]A.K. Palit, and D. Popovic, “Nonlinear Combination of Forecasts Using Artifical Neural Network, Fuzzy Logic and Neuro-Fuzzy Approaches”, The Ninth IEEE International Conference on Fuzzy Systems, 2, pp.566-571 (2000).
[63]V. A. Profillidis, “Econometric and fuzzy models for the forecast of demand in the airport of Rhodes”, Journal Air Transport Management, 6, pp.95-100 (2000).
[64]M. Tamimi, and R. Egbert, “Short term electric load forecasting via fuzzy neural collaboration”, Electric Power System Research, 56(3), pp.243-248 (2000).
[65]J. Deng, “Grey forecasting and decision”, Wuhan Huazhong University of Science and Technology Press, China (1995).
[66]D. Julong, “Control problems of Grey System”, Systems and Control letters, 1(5), pp.288-94 (1982).
[67]D. Julong, “The Essential Methods of Grey Systems”, Huazhong University of Science & Technology Press, pp.64-67 (1987).
[68]Y.T. Hsu, & E. Y. Kang, “Grey modeling of moving average index in Taiwan stock market”, Journal of Grey System, Vol. 10, No. 3, pp. 215-23 (1998).
[69]Y.T. Hsu, H.C. Cheng, & C. B. Lin, “A long-term prediction using GMs”, Journal of Grey System, Vol. 12, No. 1, pp. 41-54 (2000).
[70]Y.T. Hsu, C.B. Lin, & H. C. Cheng, “Grey model selections based on fuzzy trend prediction”, Journal of Fuzzy Mathematics, Vol. 7, No. 4, pp. 897-905 (1999).
[71]T. Y. Liu, J. Yeh,., C. M. Chen, & Y. T. Hsu, “A GreyART system for grey information processing”, Neurocomputing, Vol. 56, , January, pp. 407-414 (2004).
[72]Hua Hua, Chi Xie, Bo Sun, Huibin Chu, Ruizeng Yan. “Combining Forecasting Model of Securities Market Based on Grey Model and Neural Network”, Journal of Hunan University (Natural Sciences), 34(9):86-89 (2007).
[73]D. Julong, “Relational space of Grey Systems”, Fuzzy mathematics, (Special Issue of Grey systems) 2, pp.1-10 (1985).
[74]D. Julong, “Essential problems of Grey System Theory”, Journal of Xiangfan University, 1, pp.5-27(1986).
[75]Alex KungHsiung Chang, KuoLiang Lu, “A Study of Grey Theory on Improving the Investment Performance of Technical Analysis Index – an Example of Morgan Stanley Taiwan Index’ Component Stocks”, Proceedings of 2007 IEEE International Conference on Grey Systems and Intelligent Services, November 18-20, Nanjing, China(2007).
[76]Chun-The Lee, Yi-Ping Chen ,“The Efficacy of Networks and Simple Technical Indicators in Predicting Stock Markets”, 2007 International Conference on Convergence Information Technology (2007).
[77]J. Bohan, , “Relative strength : Further positive evidence.”, Journal of Portfolio Management, Fall, pp36-39 (1981).
[78]M. C. Jensen, , & G . Bennington, “Random walks and technical theories: Some additional evidences”, Journal of Finance, 25, pp39-52 (1970).
[79]E. H. Sorensen and T. Burke , “Portfolio returns from active industry group rotation”, Financial Analysts Journal Vol. 42 (1986).
[80]Kimmo Kiviluoto, Pentti Bergius, “Analyzing Financial Statements with the Self-Organizing Map”, Proceeding of the Workshop on Self-Organizing Maps (WSOM97), Helsinki, Finland (1997).
[81]Rie Honda, Shuai Wang, Tokio Kikuchi and Osamu Konishi, “Mining of moving objects from time-series images and its application to satellite weather imagery?”, Department of Mathematics and Information Science, Kochi University, February 11 (2002).
[82]Juha Vesanto, Esa Alhoniemi, “Clustering of the Self-Organizing Map”, IEEE Transactions on Neural Networks, Vol. 11, No.3, pp.586-600 (2000)
[83]S. M . Chen,“Forecasting enrollments based on fuzzy time series”, Fuzzy Sets and Systems, Vol. 81, pp. 311-19 (1996).
[84]S. M. Chen, ”Forecasting enrollments based on high-order fuzzy time series”, Cybernetics and Systems: An International Journal, Vol. 33, pp. l 1-16 (2002).
[85]J. R. Hwang, , S. M. Chen, & C. H. Lee , “Handling forecasting problems using fuzzy time series”, Fuzzy Sets and Systems, Vol. 100, pp. 217-28 (1998).
[86]C.-H. Lee, L., Liu, A. & Chen, W.-S. , “Pattern discovery of fuzzy time series for financial prediction”, IEEE Transactions on Knowledge and Data Engineering, Vol. 18, No. 5, May, pp. 613-625(2006).