在這篇論文中，我們提出一個模型，這個模型是應用基因規劃法訓練出可獲利且穩定的交易策略，並在測試期間運用此交易策略來交易股票。基因規劃法的變數包含6個基本資訊以及25個技術指標，我們的模型執行在台灣加權指數大約10年，從2000/9/14到2010/5/21。我們做了5個實驗，在這些實驗中，我們發現使用基因規劃法包含兩個算術樹將可以得到穩定的報酬。另外，如果我們從三個最相似現在訓練期間的歷史期間中得到交易策略，我們可以在測試期間獲得報酬。在各個實驗中，有8個不同的訓練天數，分別是90, 180, 270, 365, 455, 545, 635,以及730天，以及3個不同的測試天數，分別為90, 180, 和365天。測試期間是移動更新，直到實驗期間結束。當訓練天數為730天和測試天數是365天時，累積報酬率可以達到165.30%，比使用buy-and-hold策略1.19%高出許多。

In this thesis, we propose a model which applies the genetic programming (GP) to train the profitable and stable trading strategy in the training period, and then the strategy is applied to trade stocks in the testing period. The variables for GP in our models include 6 basic information and 25 technical indicators. We perform our models on Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) from 2000/9/14 to 2010/5/21, approximately ten years. We conduct five experiments. In these experiments, we find that the trading strategies generated by GP with two arithmetic trees have more stable returns. In addition, if we obtain the trading strategies in three historical periods which are the most similar to the current training period, we earn higher return in the testing periods. In each experiment, 24 cases are considered, with training periods of 90, 180, 270, 365, 455, 545, 635 and 730 days, and testing periods of 90, 180 and 365 days, respectively. The testing period is rolling updated until the end of the experiment period. The best cumulative return 165.30\% occurs when 730-day training period pairs with 365-day testing period, which is much higher than the return of the buy-and-hold strategy 1.19\%.

ABSTRACT . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 0
Chapter 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
Chapter 2. Preliminaries . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
2.1 Genetic Programmings . . . . . . . . . . . . . . . . . . . . . . . . . . 3
2.2 Previous Works . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.2.1 Chen’s Method for the Investment of Mutual Funds . . . . . . 8
Chapter 3. Stock Investments with Genetic Programming . . . . . . 10
3.1 The Flowchart of Investment . . . . . . . . . . . . . . . . . . . . . . . 10
3.2 Training Intervals Selection from Historical Data . . . . . . . . . . . . 10
3.3 Generating the Trading Strategy with the Genetic Programming . . . 13
3.4 Technical Indicators . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
Chapter 4. Experimental Results . . . . . . . . . . . . . . . . . . . . . . 20
4.1 Benchmarks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
4.2 Data Collection and Preprocessing . . . . . . . . . . . . . . . . . . . 20
4.3 Experimental results . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
4.3.1 Trading Strategies by Genetic Programming with One Arithmetic Tree . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
4.3.2 Trading Strategies by Genetic Programming with Two Arithmetic Trees . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
4.3.3 Trading Strategies by Genetic Programming with Two Arithmetic Trees and Feature Selection . . . . . . . . . . . . . . . . 26
4.3.4 Trading Strategies by Genetic Programming with Two Arithmetic Trees and Macroeconomic Indicators . . . . . . . . . . . 28
4.3.5 Trading Strategies by Genetic Programming with Two Arithmetic Trees and Historical Training Period . . . . . . . . . . . 29
4.4 Comparison of Various Models . . . . . . . . . . . . . . . . . . . . . . 31
Chapter 5. Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35
BIBLIOGRAPHY . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37
Appendixes
A. The Detailed Returns in All Testing Periods . . . . . . . . . . . . . 40

[1] M. A. Boyacioglu and D. Avci, “An adaptive network-based fuzzy inference system ANFIS for the prediction of stock market return: The case of the istanbul stock exchange,” Expert Systems with Applications, Vol. 37, pp. 7908–7912, 2010.
[2] T. J. Chang, S. C. Yang, and K. J. Chang, “Portfolio optimization problems in different risk measures using genetic algorithm,” Expert Systems with Applications, Vol. 36, pp. 10529–10537, 2009.
[3] H. H. Chen, C. B. Yang, and Y. H. Peng, “Genetic programming for the investment of the mutual fund with sortino ratio and mean variance model,” Proc. of the 15th Conference on Artificial Intelligence and Applications, Hsinchu, Taiwan, Nov. 2010.
[4] J. S. Chen, J. L. Hou, S. M. Wu, and Y. W. C. Chien, “Constructing investment strategy portfolios by combination genetic algorithms,” Expert Systems with Applications, Vol. 36, pp. 3824–3828, 2009.
[5] D. Y. Chiu and P. J. Chen, “Dynamically exploring internal mechanism of stock market by fuzzy-based support vector machines with high dimension input space and genetic algorithm,” Expert Systems with Applications, Vol. 36, pp. 1240–1248, 2009.
[6] R. Choudhry and K. Garg, “A hybrid machine learning system for stock machine market forecasting,” Proc. of World Academy of Science, Engineering and Technology, Vol. 39, pp. 315–318, Mar. 2008.
[7] M. R. Hassan, B. Nath, and M. Kirley, “A fusion model of HMM, ANN and GA for stock market forecasting,” Expert System with Application, Vol. 33, pp. 171–180, 2007.
[8] J. H. Holland, Adaptation in natural and artificial systems: an introduction analysis with applications to biology, control, and artificial intelligence. University of Michigan Press, 1975.
[9] W. Huang, Y. Nakamori, and S. Y. Wang, “Forecasting stock market movement direction with support vector machine,” Computers & Operations Research, Vol. 32, pp. 2513–2522, 2005.
[10] H. Ince and T. B. Trafalis, “Short term forecasting with support vector machines and application to stock price prediction,” International Journal of General Systems, Vol. 37, pp. 677–687, 2008.
[11] K. Kwon and B. R. Moon, “A hybrid neurogenetic approach for stock forecasting,” IEEE Transactions on Neural Networks, Vol. 18(3), pp. 851–864, 2007.
[12] Y. Leu, C. P. Lee, and C. C. Hung, “A fuzzy time series-based neural network approach to option price forecasting,” the 2nd Asian Conference on Intelligent Information and Database Systems, Vol. 5990, pp. 360–369, 2010.
[13] P.F.Blanco, D. Sagi, and J.I.Hdalgo, “Technical market indicators optimization using evolutionary algorithm,” Proc. of the 2008 GECCO conference companion on Genetic and evolutionary computation, Atlanta, USA, July 2008.
[14] J.-Y. Potvin, P. Soriano, and M. Vallee, “Generating trading rules on the stock markets with genetic programming,” Computers & Operations Research, Vol. 31, pp. 1033–1047, 2004.
[15] N. Powell, S. Y. Foo, and M. Weatherspoon, “Supervised and unsupervised methods for stock trend forecasting,” Proc. the 40th Southeastern Symposium on System Theory, New Orleans, LA, USA, Mar. 2008.
[16] Taiwan Economic Journal Co., Ltd, “TEJ.” http://www.tej.com.tw/twsite/Default.aspx, 1991.
[17] C. F. Tsai and Y. C. Hsiao, “Combining multiple feature selection methods for stock prediction: Union, intersection, and multi-intersection approaches,” Decision Support Systems, Vol. 50, pp. 258–269, 2010.
[18] T. J. Tsai, C. B. Yang, and Y. H. Peng, “Genetic algorithms for the investment of the mutual fund with global trend indicator,” Expert Systems with Applications, Vol. 38(3), pp. 1697–1701, 2011.
[19] T. H. K. Yu and K. H. Huang, “A neural network-based fuzzy time series model to improve forecasting,” Expert Systems with Applications, Vol. 37, pp. 3366–3372, 2010.
[20] M. Zhang and W. Smart, “Using gaussian distribution to construct fitness functions in genetic programming for multiclass object classification,” Pattern Recognition Letters, Vol. 27, pp. 1266–1274, 2006.