本篇論文中，我們利用基因表示規劃法訓練可獲利的交易策略。我們提出一個模型，它利用和當前模板區間高度相似的幾個歷史區間，並利用該區間的最佳交易策略來產生交易訊號。為保持穩定性，我們提出了以簡單多數決為基礎的交易決策機制。我們的投資標的為台灣加權指數，交易測試區間從2000/9/14到2012/1/17約十二年。在各個實驗中，訓練區間的長度分別為60, 90, 120, 180, 以及270交易日。我們觀察到我們的模型在投票門檻較高時比較能作出可獲利的交易決策。當我們訓練天數為180天且有效門檻和投票門檻分別為0.21及0.88時，累計報酬率236.25%和年化報酬率10.63%比起使用buy-and-hold策略的累計報酬率0.96%和年化報酬率0.08%高出許多。

In the thesis, we apply the gene expression programming (GEP) to training profitable trading strategies. We propose a model which utilizes several historical periods that are highly related to the current template period, and the best trading strategies of the historical periods generate the trading signals. To keep stability of our model, we proposed the trading decision mechanism based on simple majority vote in our model. The Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) is selected as our investment target and the trading period starts from 2000/9/14 to 2012/1/17, approximately twelve years. In our experiments, the lengths of our training period are 60, 90, 120, 180, and 270 trading days, respectively. We observe that the model with higher voting threshold usually can make profitable trading decisions. The best cumulative return 236.25\% and the best annualized cumulative return 10.63\% occur when the 180-day training models pairs with available threshold 0.21 and voting threshold 0.88, which are higher than the cumulative return 0.96\% and annualized cumulative return 0.08\% of the buy-and-hold strategy.

LIST OF FIGURES . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iii
LIST OF TABLES . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . v
ABSTRACT . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
Chapter 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
Chapter 2. Preliminaries . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
2.1 Gene Expression Programming . . . . . . . . . . . . . . . . . . . . . 3
2.2 Jhou’s Method . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.3 Technical Indicators . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
Chapter 3. The Trading Strategy for Stock Investment . . . . . . . . 14
3.1 The Flow Chart of Strategy Pool Implementation . . . . . . . . . . . 14
3.2 Trading Strategy Mining with the Gene Expression Programming . . 15
3.3 Cosine Distance Measurement . . . . . . . . . . . . . . . . . . . . . . 18
3.4 Our Method . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
Chapter 4. Experimental Results . . . . . . . . . . . . . . . . . . . . . . 24
4.1 Data Collection and Processing . . . . . . . . . . . . . . . . . . . . . 24
4.2 Experimental Results . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
4.2.1 Trading Signals for Trading Decision . . . . . . . . . . . . . . 25
4.3 Comparison of Various Models . . . . . . . . . . . . . . . . . . . . . . 32
Chapter 5. Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34
BIBLIOGRAPHY . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35
Appendixes
A. The Detailed Returns . . . . . . . . . . . . . . . . . . . . . . . . . . . 37

[1] D. J. Berndt and J. Clifford, “Using dynamic time warping to find patterns in
time series,” AAAI Technical Report WS-94-03, 1994.
[2] P. C. Chang, C. Y. Fan, and J. J. Lin, “Integrating a piecewise linear repre-
sentation method with dynamic time warping system for stock trading decision
making,” Fourth International Conference on Natural Computation, Sept. 2008.
[3] H. H. Chen, C. B. Yang, and Y. H. Peng, “Genetic programming for the trading
strategy of the mutual fund investment with Sortino ratio and mean variance
model,” Proc. of the 15th Conference on Artificial Intelligence and Applications,
Hsinchu, Taiwan, Nov. 2010.
[4] C. Ferreira, “Gene expression programming: A new adaptive algorithm for
solving problems,” Complex Systems, Vol. 13, pp. 87–129, 2001.
[5] Y. M. Ha, S. Park, S. W. Kim, J. I. Won, and J. H. Yoon, “A stock recommen-
dation exploiting rule discovery in stock databases,” Imformation and Software
Technology, Vol. 51, pp. 1140–1149, 2009.
[6] J. H. Holland, Adaptation in natural and artificial systems: an introduction
analysis with applications to biology, control, and artificial intelligence. Uni-
versity of Michigan Press, 1975.
[7] C. M. Hsu, “A hybrid precedure for stock price prediction by integrating self-
organizing map and genetic programming,” Expert Systems with Applications,
Vol. 38, pp. 14026–14036, 2011.
[8] S. M. Jhou, C. B. Yang, and H. H. Chen, “Taiwan stock forecasting with the
genetic programming,” Proc. of the 16th Conference on Artificial Intelligence
and Application (Domestic Track), Chungli, Taiwan, pp. 151–157, Nov. 2011.
[9] J. R. Koza, “Genetic programming: On the programming of computers by
means of natural selectio,” MIT Press, 1992.
[10] L. P. Ni, Z. W. Ni, and Y. Z. Gao, “Stock trend prediction based on fractal fea-
ture selection and support vector machine,” Expert Systems with Applications,
Vol. 38, pp. 5569–5576, 2011.
[11] T. J. Tsai, C. B. Yang, and Y. H. Peng, “Genetic algorithms for the invest-
ment of the mutual fund with global trend indicator,” Expert Systems with
Applications, Vol. 38(3), pp. 1697–1701, 2011.
[12] T. L. Wang and M. Wang, “Features extraction based on particle swarm opti-
mization for high frequency financial data,” Granular Computing (GrC), 2011
IEEE International Conference on, pp. 728–733, IEEE, 2011.