Chapter 6 Conclusions
6.2 Future Works
There is still some work needs to be improved for discovering the knowledge based on the institutional analysis, which is stated in the following.
(1) The institutional indicators are not the only determinants in the stock market, where fundamental and technical indexes should be taken into account as well. Since the influencing factors of the stock trend will change dynamically, deciding the most important and representative indexes at the time seems to be quite contributive. The significance level of each element will change as time goes by; therefore, the weight of every influencing factor should be adjusted.
(2) Extended classifier system (XCS) can be applied to simulate on the institutional stock data for being compared with the accumulated profit of LCS. That is because LCS model is strength-based system, while XCS is accuracy-based [33]. Through the experiment, some interesting rules may be discovered and a new classifier system that suits such domain may also be newly developed.
(3) In credit apportionment, other reinforcement learning approaches can be implemented into the system, such as recurrent reinforcement learning and direct learning. The above-mentioned two reinforcement learning methods are proved to be quite fit in with the dynamic optimization in the finance domain.
(4) The meaning of the final existing rules in the rule base should be particularly analyzed and discussed. If so, the subsequent price trend can be almost accurately predicted under certain discovered situations.
(5) The statistical pitfalls should be discussed for interpreting some patterns or situations that cannot be discovered or implemented through statistical tools.
58
References
1. John H. Holland, Adaptation in Natural and Artificial System, University of Michigan Press, 1975.
2. Charles M. C. Lee and Bhaskaran Swaminathan, “Price Momentum and Trading Volume”, The Journal of Finance, 5, 2000.
3. Dimitri Vittas, “Institutional Investors and Securities Markets; Which Comes First?”, ABCD LAC Conference, 1998.
4. Chiraphol N. Chiyachantana, Pankaj K. Jain, Christine Jiang, and Robert A. Wood,
“International Evidence on Institutional Trading Behavior and Price Impact”, Working Papers, University of Memphis, 2003.
5. Güler Aras and Alövsat Müslümov, “Institutional Investors and Stock Market Development: A Causality Study”, Working Papers, Dogus University, 2003.
6. Shih-Wei Lin and Lee-Ing Tong, A Study on Relationship Among Taiwan’s Weighted Stock Index, “Outstanding Balance of Margin Loan and Outstanding Balance of Stock Loan-Using Vector Error Correction Model”, Journal of Management & Systems, 4(2), 1997.
7. Sing-Ning Huang, “The Impact on the Change of Balance of Margin Purchasing and Short Selling to the Stock Returns Based on the Electronic Stocks”, National Chung Hsing University, M.S. Thesis, 1997.
8. Olan T. Henry & Michael McKenzie, “The Impact of Short Selling on the Price-Volume Relationship: Evidence from Hong Kong, European Financial Management Association Conference”, Working Papers, 869, 2003.
9. A. Ronald Gallant, Peter E. Rossi, and George Tauchen, “Stock Prices and Volume”, The Review of Financial Studies, 5(2), 1992.
59
10. John Y. Campbell, Sanford J. Grossman, and Jiang Wang, “Trading Volume and Serial Correlation in Stock Returns”, The Quarterly Journal of Economics, 108(4), pp.905-939, 1993.
11. Lawrence Blume, David Easley, and Maureen O’Hara, “Market Statistics and Technical Analysis: The Role of Volume”, The Journal of Finance, 49(1), pp.153-181, 1994.
12. Thomas W. MacFarland, Statistics Tutorials Based on SPSS and Minitab, 1998.
13. Douglas C. Montgomery, Elizabeth A. Peck, and G. Geoffrey Vining, “Introduction to Linear Regression Analysis”, Student Solutions Manual, 3rd Edition, 2001.
14. John H. Holland, Keith J. Holyoak, Richard E. Nisbett, and P. R. Thagard, Induction:
Processes of Inference, Learning, and Discovery, MIT Press, Cambridge, 1986.
15. Tim Kovacs, “What Should a Classifier System Learn and How Should We Measure It?”, Soft Computing, 6, pp.171-182, 2002.
16. Stewart W. Wilson, “Generalization in the XCS Classifier System”, Proceedings of the Third Annual Conference on Genetic Programming, 1998.
17. Marco Colombetti and Marco Dorigo, “Training Agents to Perform Sequential Behavior”, Adaptive Behavior, 2(3), pp.247-275, 1994.
18. Andreas Geyer-Schulz, “Holland Classifier Systems”, Proceedings of the International Conference on Applied Programming Languages, pp.43-55, 1995.
19. John H. Holmes, Learning Classifier Systems: From Foundations to Applications, Spring-Verlag Berlin Heidelberg, 2000.
20. Joseh Maria Garrell i Guiu, Elisabet Golobardes i Ribé, Ester Bernadó i Mansilla, and Framcesc Xavier Llorà i Fàbrega, “Automatic Diagnosis with Genetic Algorithms and Case-Based Reasoning”, AIENG Journal, 13, pp.367-372, 1999.
21. Chao-Fang Chen, “A Dynamically Adaptive Routing Method Based on Classifier Systems”, National Chiao Tung University, M.S. Thesis, 2000.
22. Pen-Yang Liao and Jiah-Shing Chen, “Dynamic Trading Strategy Learning Model Using
60
Learning Classifier Systems”, Proceedings of the 2001 Congress on Evolutionary Computation, 2, pp.27-30, 2001.
23. Robert A. Richards and Sheri D. Sheppard, “A Learning Classifier System for Three-Dimensional Shape Optimization”, Parallel Problem Solving from Nature – PPSN IV, LNCS, 1141, pp.1032-1042, 1996.
24. Robert E. Smith, B.A. Dike, B. Ravichandran, A. El-Fallah, and R.K. Mehra, “The Fighter Aircraft LCS: A Case of Different LCS Goals and Techniques”, Proceedings of The 1999 Genetic and Evolutionary Computation Conference Workshop Program, pp.283-300, 1999.
25. Peter W. Frey and David J. Slate, “Letter Recognition Using Holland-Style Adaptive Classifiers”, Machine Learning, 6(2), pp.161-182, 1991.
26. Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, MIT Press, Cambridge, MA, 1998.
27. Mance E. Harmon and Stephanie S. Harmon, Reinforcement Learning: A Tutorial, 1996.
28. John H. Holland, “Properties of the Bucket Brigade Algorithm”, Proceedings of an International Conference on Genetic Algorithms and Their Applications, pp.1-7, 1985.
29. Christopher JCH Watkins and Peter Dayan, “Technical Note: Q-Learning”, Machine Learning, 8, pp.279-292, 1992.
30. Jiawei Han and Micheline Kamber, Data Mining: Concepts and Techniques, Academic Press, 2001.
31. Gen-Huey Chen, Ming-Yang Kao, Yuh-Dauh Lyuu, and Hsing-Kuo Wong, “Optimal Buy-and-Hold Strategies for Financial Markets with Bounded Daily Returns”, SIAM Journal on Computing, 31(2), 2001.
32. Marco Dorigo and Hugues Bersini, “A Comparison of Q-Learning and Classifier Systems, Proceedings of From Animats”, Third International Conference on Simulation of Adaptive Behavior, MIT Press, pp.248-255, 1994.
61
33. Stewart W. Wilson, “Classifier Fitness Based on Accuracy”, Evolutionary Computation, 3(2), pp.149-175, 1995.
62
Appendix
Table 11 Correlation Test of UMC
Table 12 Correlation Test of Foxconn
63
Table 13 Correlation Test of Cathay
Table 14 Correlation Test of Fubon
64
Table 15 Correlation Test of Mega
Table 16 Correlation Test of CSC
65
Table 17 Correlation Test of NPC
Table 18 Correlation Test of FPC
66