臺灣博碩士論文加值系統

在經濟的蓬勃發展與財富的快速累積下，股票投資在台灣目前已經是個非常重要的投資活動，但是，投資者身處於目前投資標的眾多及環境快速變動下，常因對投資標的不了解或是盲目的投資造成損失。因此，建立一個客觀有效的投資決策支援系統幫助投資人做正確決策已成為一熱門的研究領域。類神經網路是一擁有傑出股價預測能力之資料探勘技術，但其並無法清楚表明其預測的規則，易導致投資者無法有可靠的根據作判斷，決策樹則是一可詳細描述預測規則的資料探勘技術。在以往的研究中已證明混合式與結合式模型的預測能力優於單一模型，但尚未在股價預測領域使用。因此，本研究結合類神經網路與決策樹技術，使用可公開下載之台灣經濟新報資料庫之電子業股票配合滑動視窗法驗證模型之正確性。實驗結果顯示，本模型在電子產業股價漲跌預測之正確率達到77%，且結合式模型的預測能力在股價預測領域也確實優於單一模型。此外，決策樹也詳細提供了一套可作為投資判斷的預測規則。

Stock investment has become an important investment activity in Taiwan when economic becomes well developed and wealth accumulated so fast. However, investors usually get loss by unknown investment objective and invest blindly because of various investment objectives and the unpredictable economic environment. Therefore, to create a good investment decision support system to assist investors making good decisions has become an important research problem. Artificial Neural Networks (ANN) are a data mining technique that has good performances in forecasting stock price. However, the major limitation is that it can not explain the forecasting decisions clearly as a black box system. On the other hand, a decision tree model can generate some rules to describe the forecasting decisions. In literature except stock price forecasting, combining a number of different models as the hybrid model has shown better forecasting performances than many single models. Therefore, this thesis focus on the electronic industry stock by the TEJ database and combining ANN and decision trees to create a stock price forecasting model. The experimental result shows that this combined model has 77% accuracy in the electronic industry than the single ANN and decision tree models. In addition, the decision tree model in the combined hybrid model provides reliable forecasting rules to assist investment decision making.

摘要 II
Chapter1. Introduction 1
1.1 Research background and motivation 1
1.2 Research objectives 4
1.3 Organization of the thesis 6
Chapter 2. Literature review 7
2.1 Stock price forecast 7
2.1.1 Stock price and related variables 7
2.1.2 Stock price theory 7
2.2 Stock price forecast method 10
2.3 Data mining 12
2.3.1 The definition of data mining 12
2.3.2 Artificial Neural Network 14
2.3.2.1 Introduction 14
2.3.2.2 ANN model 15
2.3.3 Decision tree 21
2.3.3.1 Introduction 21
2.3.3.2 The decision tree model 22
2.4 Related work 25
Chapter3. Experimental Methodology 31
3.1 Introduction 31
3.2 The source of data collection 33
3.3 Variable Selection 34
3.4 Establish baseline models 36
3.4.1 The ANN model 37
3.4.2 Decision trees 38
3.5 Combining ANN with decision trees 39
3.5.2 The Combination Process 39
3.5 Evaluation strategies 41
Chapter4. Experimental results and analysis 43
4.1 ANN 44
4.2 Decision tree 44
4.3 Combined decision tree and ANN 45
4.4 Combined decision tree and decision tree 47
4.5 Comparisons and discussions 48
4.5.1 Comparisons among ANN, DT, DT+ ANN and DT+DT method 48
4.5.2 Describe forecast rules 51
Chapter 5 Conclusion and Future Work 56
5.1 Summary of this research 56
5.2 Contribution 57
5.3 Future work 57
5.3.1 Techniques used 57
5.3.2 Variables choose 58
5.3.3 Industry used 58
References 59

References

Aguado, T. Montoya, L. Borras, A. Seco and J. Ferrer (2008) “Using SOM and PCA for analysing and interpreting data from a P-removal SBR” Engineering Applications of Artificial Intelligence Volume 21, Issue 6, September 2008, 919-930
Balvers, R. J., T. F. Cosimano, , and B. McDonald, (1990). “Predicting stock returns in an efficient market”. Journal of Finance, 55, 1109–1128.
Breen, W., L. R. Glosten, and R. Jagannathan, (1990). “Predictable variations in stock index returns”. Journal of Finance, 44, 1177–1189
Burrell, P. R. and B. O. Folarin, (1997). “The impact of neural networks in finance.” Neural Computing & Applications, 6, 193–200.
Campbell, J. (1987). “Stock returns and the term structure.” Journal of Financial Economics, 18, 373–399.
Chang, P. C., Y. W. Wang, and W. N. Yang,. (2004). “An investigation of the hybrid forecasting models for stock price variation in Taiwan.” Journal of the Chinese Institute of Industrial Engineering, 21(4), 358–368.
Chen, A.S. , T. Mark, Leung, and D. Hazem.(2003)” Application of neural networks to an emerging financial market: forecasting and trading the Taiwan Stock Index“ Computers & Operations Research 30, 901-923
Chung, B.C., w. Yen, Wang, and W. N. Yang (2004)“An investigation of the hybrid forecasting models for stock price variation in Taiwan” Journal of the Chinese Institute of Industrial Engineers, Vol. 21, No. 4, 358-368
Christian, S. and T. Mark, (2008)“Identifying multiple outliers in heavy-tailed distributions with an application to market crash” Journal of Empirical Finance Volume 15, Issue 4, September 2008, Pages 700-713
Cordinly, W.G.. (1907). “Guide To The Stock Exchange”
David, E. and T. Suraphan, (2005) “The use of data mining and neural networks for forecasting stock market returns“. Expert Systems with Applications 29 ,927–940
Dennis, O. and M. Charles, (2003)“Neural network forecasts of Canadian stock returns using accounting ratios “International Journal of Forecasting 19 (2003) 453–465
Fama, E. F.and W. G. Schwert, (1977). “Asset returns and inflation.” Journal of Financial Economics, 5, 115–146.
Fama, E. F. (1970). “Efficient capital markets: A review of theory and empirical work.” Journal of Finance, 25, 383–417.
Fama, E. F., and K. R. French, (1989). “Business conditions and expected returns on stocks and bonds.” Journal of Financial Economics, 25, 23–49.
Ferson, W. (1989). “Changes in expected security returns, risk, and the level of interest rates.” Journal of Finance, 44, 1191–1217.
Glen D. and K. Mark (1997)“ An artificial neural network-GARCH model for international stock return volatility “ Journal of empirical finance 4 (1997 ) 17-46
Hui, Z., T. Hastiey, and R. Tibshiraniz, (2004) “Sparse Principal Component Analysis” April 26, 2004
Hopfiled, J. J. (1982) “Neural Networks and Physical Systems with Emergent Collective Computational abilities.” Proceedings of the National Academy of Sciences, 79, 2554-2558.
Kim, H.J. and K.S. Shin, “A hybrid approach based on neural networks and genetic algorithms for detecting temporal patterns in stock markets” Applied Soft Computing 7 (2007) 569–576
King, B. (1966) “Market and Industry factor in Stock Price Behavior”. Journal of Business, 39,129-140
Keim, D., and R. Stambaugh, (1986). “Predicting returns in the stock and bond
markets.” Journal of Financial Economics, 17, 357–390.
Kunhuang H. and H.K. YU, (2006) “The application of neural networks to forecast fuzzy time series” Physical A 363 ()2006 481-491
Lei, S. and G. Chen, (2008) “Detection of outliers in multilevel models” Journal of Statistical Planning and Inference Volume 138, Issue 10, 1 October 2008, Pages 3189-3199
Lo, A. W., H. Mamaysky, and J. Wang, (2000). “Foundation of technical analysis: computations, algorithms, statistical inference, and empirical implementation.” Journal of Finance, 55(4), 1705–1765.
McCulloch, W.S.and W. Pitts, (1943) “A Logical Calculus and the Ideas Immanent in the Nervous Activity.” Bulletin of Mathematical Biophysics, 5, 115-133
Md, R. H. , B. Nath,, and M. Kirley, (2007)“A fusion model of HMM, ANN and GA for stock market forecasting “ Expert Systems with Applications 33 (2007) 171–180
Mills, T. C. (1990). “Non-linear time series models in economics.” Journal of Economic Surveys, 5, 215–241.
Niall O. and G.M. Madden. (2006)“ A neural network approach to predicting stock exchange movements using external factors” Knowledge-Based Systems 19 (2006) 371–378
Olson, D. and C. Mossman, (2003) “ Neural network forecasts of Canadian stock returns using accounting ratios”. International Journal of Forecasting, 19(3), 453-465.
Panayiotis, C.A., C. Charalambous, and S.H. Martzoukos (2008)“Pricing and trading European options by combining artificial neural networks and parametric models with implied parameters” European Journal of Operational Research 185 (2008) 1415–1433
Perez-Rodriguez, Jorge V.Torra, SalvadorAndrada-Felix, and Julian (2005)“STAR and ANN models: forecasting performance on the Spanish "Ibex-35" stock index” Journal of Empirical Finance 12 (2005) 490-509
Quah, T.S. and B. Srinivasan (1999) “Improving returns on stock investment through neural network selection” Expert Systems with Applications 17 (1999) 295–301
Ramazan, G. (1996) “Non-linear prediction of security returns with moving average rules” Journal of Forecasting, Volume 15, Issue 3 165-174
Roh, T.H. (2006) “Forecasting the volatility of stock price index” Expert Systems with Applications: An International Journal Volume 33 (November 2007) ,916-922
Rumelhart, D.E., G.E Hinton, and R.J. Williams, (1986) “Learning internal representation by error propagation. ”. Parallel Distributed Processing, Vol.1,99.318-362.
Schwert, W. (1990). “Stock returns and real activity: a century of evidence.” Journal of Finance, 45, 1237–1257.
Sorensen, E.H., K.L. Miller, and C.K. Ooi, (2000) “The Decision Tree Approach to Stock Selection – An evolving tree model performs the best”. Journal of portfolio Management, 42-52
Swales, G. S., and Y. Yoon, (1992) “Applying artificial neural network to investment analysis” . Financial Analysts Journal, 48, 78-80
Thomassey, S.and A. Fiordaliso, (2006) “A Hibrid sales forecasting system based on clustering and decision tree”. Decision Support systems, 42, 408-421
Wu M.C., S.Y. Lin, and C.H. Lin. “An effective application of decision tree to stock trading” Expert Systems with Applications 31 (2006) 270–274
Wang, Y.H. (2007) “Nonlinear neural network forecasting model for stock index option price: Hybrid GJR–GARCH approach“ Expert Systems with Applications xxx (2007) xxx–xxx
Wanga, J.L. and S.H. Chan, (2006) “Stock market trading rule discovery using two-layer bias decision tree” Expert Systems with Applications 30 (2006) 605–611
Yao, J., C.L. Tan, and H.L. Pok, (1990) “Neurl Networks for technical analysis: A Study on KLCI”. International journal of Theoretical and Applied Finance, 2(2), 221-241
Zhu, X., H. Wang, L. Xu, and H. Li (2007)“Predicting stock index increments by neural networks: The role of trading volume under different horizons“ Expert Systems with Applications xxx (2007) xxx-xxx
Zarandi ,M.H., B. Rezaee, I.B. Turksen, and E. Neshat.(2007). “A type-2 fuzzy rule-based expert system model for stock price analysis” Expert Systems with Applications (2007)