在本論文中，我們假定歷史會重複出現，因此我們能利用過去的歷史資料來獲得交易策略，並套用於最新的交易日。我們利用基因表達規劃法配合一些廣為人知的技術指標做為特徵直，於相似的歷史區間中訓練出一群的交易策略，並套用於交易日的前幾十天，進一步確認這些策略是適用於交易日。最後，收集合適的交易策略，並採多數決方式投票，形成最後的買賣共識。我們的訓練區間是由1996年初到2012年底，測試區間是由2000年初到2012年底。投資標的是根據台灣100支大型上市股票其每日的的平均報酬率所自行做成的指數。在實驗一中，最好的參數組合平均可獲得報酬率為548.97% (年化報酬率為15.47%)，在實驗二中，我們增加策略的多樣性，最好的參數組合平均可獲得報酬率為685.31(年化報酬率為17.18%)。這兩結果都優於buy-and-hold方式的報酬率 (287.00%)。

In this thesis, we assume that history will repeat itself, so we could find out good trading strategies from the historical series and apply them in the future. The profitable strategies are trained out by the gene expression programming (GEP), which involves some well-known stock technical indicators as features.
Our data set collects the 100 stocks with the top capital from the listed companies in the Taiwan stock market. Based on the accumulated average daily return of the close prices of these stocks, we build a new series called portfolio index as the investment target. For each trading day, we search for some similar template intervals from the historical data and pick out the pertained trading strategies from the strategy pool.
These strategies are validated by the return during a few days before the trading day to check whether each of them is profitable or not. Then these suitable strategies decide the buying or selling consensus signal with the majority vote on the trading day.
The training period is from 1996/1/6 to 2012/12/28, and the testing period is from 2000/1/4 to 2012/12/28. Two simulation experiments are performed. In experiment 1, the best average accumulated return is 548.97% (average annualized return is 15.47%). In experiment 2, we increase the diversity of trading strategies with more training. The best average accumulated return is increased to 685.31% (average annualized return is 17.18%). These two results are much better than by that of the buy-and-hold strategy, whose return is 287.00%.

LIST OF FIGURES . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iii
LIST OF TABLES . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . v
ABSTRACT . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 0
Chapter 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
Chapter 2. Preliminaries . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
2.1 Gene Expression Programming . . . . . . . . . . . . . . . . . . . . . 4
2.2 Dynamic Time Warping . . . . . . . . . . . . . . . . . . . . . . . . . 9
2.3 Technical Indicators . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
2.3.1 Moving Average . . . . . . . . . . . . . . . . . . . . . . . . . . 11
2.3.2 Exponential Moving Average . . . . . . . . . . . . . . . . . . . 11
2.3.3 Momentum . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
2.3.4 Oscillator . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
2.3.5 Relative Strength Index . . . . . . . . . . . . . . . . . . . . . 12
2.3.6 Chande Momentum Oscillator . . . . . . . . . . . . . . . . . . 14
2.3.7 Bias Ratio . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
2.3.8 Moving Average Convergence Divergence . . . . . . . . . . . . 15
2.3.9 Total Amount Per Index . . . . . . . . . . . . . . . . . . . . . 15
2.3.10 On Balance Volume . . . . . . . . . . . . . . . . . . . . . . . . 15
Chapter 3. Our Method . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
3.1 Construction of the Data Set . . . . . . . . . . . . . . . . . . . . . . . 16
3.2 The Overview of Our Method . . . . . . . . . . . . . . . . . . . . . . 17
3.3 Trading Strategy Training . . . . . . . . . . . . . . . . . . . . . . . . 19
3.3.1 Features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
3.3.2 Trading Strategy Mining . . . . . . . . . . . . . . . . . . . . . 23
3.4 Trading Consensus Signals in the Testing Period . . . . . . . . . . . . 24
Chapter 4. Experimental Results . . . . . . . . . . . . . . . . . . . . . . 27
4.1 Experimental Environment . . . . . . . . . . . . . . . . . . . . . . . . 27
4.2 The First Experiment . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
4.3 Trading Similarity Test of Near Parameters . . . . . . . . . . . . . . . 35
4.4 The Second Experiment . . . . . . . . . . . . . . . . . . . . . . . . . 38
4.5 Statistics of Features . . . . . . . . . . . . . . . . . . . . . . . . . . . 41
Chapter 5. Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45
BIBLIOGRAPHY . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46

[1] D. J. Berndt and J. Clifford, "Using dynamic time warping to find patterns in time series," Association for the Advancement of Artificial Intelligence Technical Report, pp. 395-370, 1994.
[2] P. C. Chang, C. Y. Fan, and J. J. Lin, "Integrating a piecewise linear representation method with dynamic time warping system for stock trading decision making," Fourth International Conference on Natural Computation, Vol. 2, Jinan, China, pp. 434-438, Oct. 2008.
[3] H. H. Chen, C. B. Yang, and Y. H. Peng, "The trading on the mutual funds by gene expression programming with sortino ratio," Applied Soft Computing, Vol. 15, pp. 219-230, 2014.
[4] C. Ferreira, "Gene expression programming: A new adaptive algorithm for
solving problems," Complex Systems, Vol. 13, pp. 87-129, 2001.
[5] C. M. Hsu, "A hybrid procedure for stock price prediction by integrating self-organizing map and genetic programming," Expert Systems with Applications, Vol. 38, pp. 14026-14036, 2011.
[6] C. H. Huang, C. B. Yang, and H. H. Chen, "Trading strategy mining with gene expression programming," Proc. of the 2013 International Conference on Applied Mathematics and Computational Methods in Engineering, Rhodes Island, Greece, pp. 37-42, July 2013.
[7] C. F. Huang, "A hybrid stock selection model using genetic algorithms and support vector regression," Applied Soft Computing, Vol. 12, pp. 807-818, 2012.
[8] C. F. Huang, B. R. Chang, D. W. Cheng, and C. H. Chang, "Feature selection and parameter optimization of a fuzzy-based stock selection model using genetic algorithms," International Journal of Fuzzy Systems, Vol. 14, No. 1, pp. 65-75, 2012.
[9] 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.
[10] J. R. Koza, Genetic Programming: On the programming of computers by means of natural selection, Vol. 1. Cambridge, USA, MA: MIT press, 1992.
[11] L. P. Ni, Z. W. Ni, and Y. Z. Gao, "Stock trend prediction based on fractal feature selection and support vector machine," Expert Systems with Applications, Vol. 38, pp. 5569-5576, 2011.
[12] J.-Y. Potvin, P. Soriano, and M. Vallee, "Generating trading rules on the stock markets with genetic programming," Computers & Operations Research, Vol. 31, No. 7, pp. 1033-1047, 2004.
[13] Ryan J. O'Neil, "Gene Expression Programming for Python." https://code.google.com/p/pygep/, 2007.
[14] Taiwan Economic Journal Co., Ltd, "TEJ." http://www.tej.com.tw/twsite/, 1991.
[15] 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.
[16] F. Wang, P. L. Yu, and D. W. Cheung, "Complex stock trading strategy based on particle swarm optimization," IEEE Conference on Computational Intelligence for Financial Engineering & Economics (CIFEr), New York, USA, pp. 1-6, Mar. 2012.
[17] W. Yan and C. D. Clack, "Evolving robust gp solutions for hedge fund stock selection in emerging markets," Soft Computing, Vol. 15, No. 1, pp. 37-50, 2011.
[18] L. Zhang, N. Liu, and P. Yu, "A novel instantaneous frequency algorithm and its application in stock index movement prediction," IEEE Journal of Selected Topics in Signal Processing, Vol. 6, No. 4, pp. 311-318, 2012.