柔性演算法在台指選擇權之投資應用

The Application of Soft Computing in Investing TAIEX Options

徐志明(Chih-Ming Hsu)；徐瑞民(Jui-Min Hsu)

基因規劃 ； 倒傳遞類神經網路 ； 支援向量迴歸 ； 台指選擇權 ； Genetic Programming ； Backpropagation Neural Network ； Support Vector Regression ； Options

明新學報

39卷2期（2013 / 08 / 01）

157 - 178

繁體中文

本研究利用基因規劃、倒傳遞類神經網路及支援向量迴歸，建構台灣股票大盤指數之預測模型，並擬定三種選擇權操作策略，以配合預測績效最佳的大盤指數預測模型，進行台指選擇權投資操作，以此建構一個協助投資者進行選擇權投資的系統程序。本研究以2011年1月19日至2012年1月18日的台指選擇權投資為範例，展示本研究所提出投資程序之其可行性和有效性。實證結果顯示，對於絕大部分的投資案例，基因規劃預測模型的績效表現最好；此外，操作策略三（保守操作原則）可以獲得最佳之整體投資報酬率，且所有操作策略都擁有遠高於投資期間台灣股票大盤指數之報酬率。因此，本研究所提出之選擇權投資程序，的確可協助投資者在未來實際運用於選擇權之投資操作，以期望獲取比股市大盤更佳之投資報酬率。

This study applies genetic programming, a backpropagation neural network and support vector regression to construct models for predicting Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX). Three strategies for options investment are then developed. Finally, these investment strategies coupled with the model with the best prediction performance are utilized to invest in options. The feasibility and effectiveness of the proposed systematic procedure for options investment are illustrated by a case study from 2011/01/19 to 2012/01/18 in TAIEX options market. The implementation results reveal that the genetic programing models have the best prediction performance in almost all of the investment cases. The third investment strategy (conservative operating principles) provides the highest return on investment (ROI). Furthermore, all of the ROIs regarding the three investment strategies in this study are positive and are larger than the ROI in the overall stock market substantially. Therefore, the proposed procedure can indeed assist investors in investing in Taiwan options market thus obtaining a much higher ROI.

1. Hsu, C. W., Chang, C. C. and Lin, C. J. (2003). A practical guide to support vector classification, available at: http://www.csie.ntu.edu.tw/~cjlinlpapers/guide/guide.pdf.
2. Chang, C.-C. and Lin, C.-J. (2012). http://www.csie.ntu.edu.tw/~cjlin/libsvm/.
3. 台灣期貨交易所(2012) 。http://www.taifex.com.tw./chinese/7/AnnualTrading.asp 。
4. Ben, K. I.,Weihs, C.,Limam, M.(2010).Support vector regression control charts for multivariate nonlinear autocorrelated processes.Chemometrics and Intelligent Laboratory Systems,103(1),76-81.
5. Chiang, M.-H.,Huang, H.-Y.(2011).Stock market momentum, business conditions, and GARCH option pricing models.Journal of Empirical Finance,18(3),488-505.
6. Ciglarič, I.,Kidrič, A.(2006).Computer-Aided Derivation of the Optimal Mathematical Models to Study Gear-Pair Dynamic by Using Genetic Programming.Structural and Multidisciplinary Optimization,32(2),153-160.
7. Cortes, C.,Vapnik, V.(1995).Support-vector networks.Machine Learning,20(3),273-297.
8. Drucker, H.,Burges, C. J.,Kaufman, L.,Smola, A.,Vapnik, V.(1997).Support vector regression machines.Advances in Neural Information Processing Systems,Cambridge, MA:
9. Fausett, L.(1994).Fundamentals of Neural Networks: Architecture, Algorithms, and Applications.New Jersey:Prentice-Hall.
10. Holland, J. H.(1975).Adaptation in Natural and Artificial Systems.Ann Arbor, MI:University of Michigan Press.
11. Kavaklioglu, K.(2011).Modeling and prediction of Turkey's electricity consumption using support vector regression.Applied Energy,88(1),368-375.
12. Koza, J. R.(1992).Genetic Programming: On the Programming of Computers by Means of Natural Selection.Cambridge, MA:MIT Press.
13. Koza, J. R.,Keane, M. A.,Streeter, M. J.,Mydlowec, W.,Yu, J.,Lanza, G.(2005).Genetic Programming IV: Routine Human-Competitive Machine Intelligence.New York:Springer.
14. Koza, J. R.,Streeter, M. J.,Keane, M. A.(2008).Routine High-Retum Human-Competitive Automated Problem-Solving by Means of Genetic Programming.Information Sciences,178(23),4434-4452.
15. Kumar, S.(2004).Neural Neetworks: A Classroom Approach.New Delhi:Tata McGraw-Hill.
16. Li, D. C.,Liu, C. W.,Fang, Y. H.,Chen, C. C.(2010).A yield forecast model for pilot products using support vector regression and manufacturing experience-the case of large-size polarizer.International Journal of Production Research,48(18),5481-5496.
17. Liang, X.,Zhang, H.-S.,Mao, J.-G.,Chen, Y.(2009).Improving option price forecasts with neural networks and support vector regressions.Neurocomputing,72(13-15),3055-3065.
18. Meissner, G.,Kawano, N.(2001).Capturing the volatility smile of options on high-tech stocks-A combined GARCH-neural network approach.Journal of Economics and Finance,25(3),276-296.
19. Park, H.,Lee, J.(2012).Forcasting nonnegative option price distributions using Bayesian kernel methods.Expert Systems with Applications,39(18),13243-13252.
20. Stentoft, L.(2011).American option pricing with discrete and continuous time models: an empirical comparison.Journal of Empirical Finance,18(5),880-902.
21. Tseng, C.-H.,Cheng, S.-T.,Wang, Y.-H.,peng, J.-T.(2008).Artificial neural network model of the hybrid EGARCH volatility of the Taiwan stock index opton prices.Physica A: Statistical Mechanics and its Applications,387(13),3192-3200.
22. Vapnik, V. N.(1998).Statistical Learning Theory.New York:Wiely.
23. Vapnik, V. N.(1995).The Nature of Statistical Learning Theory.New York:Springer-Verlag.
24. Vapnik, V.,Golowich, S.,Smola, A.(1997).Support vector method for function approximation, regression estimation, and signal processing.Advances in Neural Information Processing Systems,9,281-287.
25. Wang, C.-P.,Lin, S.-H.,Huang, H.-H.,Wu, P.-C. (2012).(2012).Using neural network for forecasting TXO price under different volatility models.Expert Systems with Applications,39(5),5025-5032.
26. Wang, Y.-H.(2009).Using neural network to forecast stock index option price: a new hybrid GARCH approach.Quality & Quantity,43(5),833-843.
27. Yang, C. C.,Shieh, M. D.(2010).A support vector regression based prediction model of affective responses for product form design.Computers & Industrial Engineering,59(4),682-689.
28. Zapart, C. A.(2003).Beyond Black-Scholes: a neural networks-based approach to options pricing.International Journal of Theoretical and Applied Finance,6(5),469-489.
29. Zhang, H.-Y.(2012).Research on factors influencing European option price by using hybrid neural network.Advances in Intelligent and Soft Computing,144(10),247-252.