遺傳神經網路股票買賣決策系統的實證

Applications of Stock Trading Decision System Using Genetic Neural Networks

10.6188/JEB.2008.10(4).06

黃兆瑜(Chao-Yu Huang)；葉怡成(I-Cheng Yeh)；連立川(Li-Chuan Lien)

股票市場 ； 技術指標 ； 遺傳演算法 ； 類神經網路 ； stock market ； technical index ； genetic algorithms ； neural networks

電子商務學報

10卷4期（2008 / 12 / 01）

821 - 848

繁體中文

本研究採用「強化式」機器學習策略，跳過建構股價漲跌預測系統，而直接建構遺傳神經網路(Genetic Neural Networks, GNN)買賣決策系統，並針對台灣股市實證幾個重要的課題。研究結果顯示：在大盤指數方面，在GNN的演化過程中，確實可以觀察到「訓練期間績效與測試期間績效相關」與「隨著演化世代增加績效增加」現象，顯示GNN確實學習到具普遍化獲利能力的大盤交易策略。使用包含成交量的資訊產生的系統如果能避免過度學習，可以提高投資績效。使用短訓練期間（4.5年）的系統的獲利明顯小於使用長訓練期間（12年）者，顯示4.5年的訓練期間太短，不足以學習到具普遍化獲利能力的交易策略。使用「多遺傳神經網路多數決策略」顯示採用多數決策略無助於提高對大盤的投資績效，但可使其更穩定。在類股指數方面，其獲利能力等同買入持有策略，顯示GNN決策系統無法提高類股投資績效。

This study employed ”Reinforced Learning” strategy to bypass stock price fluctuation prediction stage and construct stock trading decision system using Genetic Neural Networks (GNN) directly. The system was validated by several important topics aiming at Taiwan stock market. The results showed the following conclusions. (1) In the evolution process of GNN with regard to stock index of Taiwan, two phenomena can be observed. First, the training period performance is correlated with test period performance. Second, the performance increases with each evolution generation of GNN. These two phenomena demonstrated that GNN can learn the general profitable trading strategy on stock index of Taiwan. (2) The trading system using price as well as volume information could increase investment performance if it can avoid over-learning. (3) The profit of the trading system using short period information (4.5 years) is obviously smaller than that using long period information (12 years). It demonstrated that 4.5 years is too short to learn the general profitable trading strategy. (4) Using ”majority decision strategy based on multi-GNNs” can not increase the mean but can reduce the standard deviation of profit. It demonstrated that this strategy is useful to improve the stability of investment performance on Taiwan stock market. (5) With regard to sector index, the profit of the trading system is about the same as the buy-and-hold strategy. It demonstrated that the system can not increase the investment performance on the sector index.This study employed ”Reinforced Learning” strategy to bypass stock price fluctuation prediction stage and construct stock trading decision system using Genetic Neural Networks (GNN) directly. The system was validated by several important topics aiming at Taiwan stock market. The results showed the following conclusions. (1) In the evolution process of GNN with regard to stock index of Taiwan, two phenomena can be observed. First, the training period performance is correlated with test period performance. Second, the performance increases with each evolution generation of GNN. These two phenomena demonstrated that GNN can learn the general profitable trading strategy on stock index of Taiwan. (2) The trading system using price as well as volume information could increase investment performance if it can avoid over-learning. (3) The profit of the trading system using short period information (4.5 years) is obviously smaller than that using long period information (12 years). It demonstrated that 4.5 years is too short to learn the general profitable trading strategy. (4) Using ”majority decision strategy based on multi-GNNs” can not increase the mean but can reduce the standard deviation of profit. It demonstrated that this strategy is useful to improve the stability of investment performance on Taiwan stock market. (5) With regard to sector index, the profit of the trading system is about the same as the buy-and-hold strategy. It demonstrated that the system can not increase the investment performance on the sector index.

1. 連立川、葉怡成(2008)。以遺傳神經網路建構台灣股市買賣決策系統之研究。資訊管理學報，15(1)，29-52。
   連結：
2. Allen, F.,Karjalainen, R.(1999).Using genetic algorithms to find technical trading rules.Journal of Finance Economics,51(2),245-271.
3. Armano, G.,Marchesi, M.,Murru, A.(2005).A hybrid genetic-neural architecture for stock indexes forecasting.Information Sciences,170(1),3-33.
4. Armano, G.,Murru, A.,Roli, F.(2002).Stock market prediction by a mixture of genetic-neural experts.International Journal of Pattern Recognition and Artificial Intelligence,16(5),501-526.
5. Booker, L. B.,Goldberg, D. E.,Holland, J. H.(1989).Classifier systems and genetic algorithms.Artificial Intelligence,40(1-3),235-282.
6. Enke, D.,Thawornwong, S.(2005).The use of data mining and neural networks for forecasting stock market returns.Expert Systems with Applications,29(4),927-940.
7. Hayward, S.(2004).Setting up performance surface on an artificial neural network with genetic algorithm optimization: In search of an accurate and profitable prediction for stock trading.Proceedings, 2004 Congress on Evolutionary Computation.
8. Holland, J. H.(1975).Adaptation in Natural and Artificial Systems.University of Michigan, Ann Arbor, MI.
9. Kim, K.,Han, I.(2000).Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index.Expert Systems with Applications,19(2),125-132.
10. Kuo, R. J.,Chen, C. H.,Hwang, Y. C.(2001).An intelligent stock trading decision support system through integration of genetic algorithm based fuzzy neural network and artificial neural network.Fuzzy Sets and Systems,118(1),21-45.
11. Kwon, Y. K.,Moon, B. R.(2003).Daily Stock Prediction Using Neuro-Genetic Hybrids.Genetic and Evolutionary Computation Conference 2003
12. Lam, M.(2004).Neural network techniques for financial performance prediction: integrating fundamental and technical analysis.Decision Support Systems,37(4),567-581.
13. Lee, R. S. T.(2004).iJADE stock advisor: An intelligent agent based stock prediction system using hybrid RBF recurrent network.IEEE Transactions on Systems, Man, and Cybernetics Part A,34(3),421-428.
14. Massimiliano, V.,Rushi, B.,Oliver, H.,Mark, S.(2004).Predicting the exchange traded fund DIA with a combination of genetic algorithms and neural networks.Expert Systems with Applications,27(3),417-425.
15. Olson, D.,Mossman, C.(2003).Neural network forecasts of Canadian stock returns using accounting ratios.International Journal of Forecasting,19(3),453-465.
16. Phua, H. P. K.,Ming, D.,Lin, W.(2001).Neural network with genetically evolution algorithms for stocks prediction.Asia-Pacific Journal of Operation Research,18(1),103-108.
17. 李建輝(2002)。碩士論文(碩士論文)。東吳大學經濟學系。
18. 周慶華(2000)。碩士論文(碩士論文)。輔仁大學金融研究所。
19. 林建成(2001)。碩士論文(碩士論文)。東吳大學經濟學系。
20. 林耀堂(2001)。碩士論文(碩士論文)。國立中央大學資訊管理研究所。
21. 連立川(2005)。碩士論文(碩士論文)。中華大學土木工程學系。
22. 葉怡成(2006)。類神經網路模式應用與實作。台北:儒林書局。
23. 劉克一(2000)。碩士論文(碩士論文)。真理大學管理科學研究所。

1. 鄭榮祿、蔡賢亮、楊崇宏、周照偉、牟聖遠(2015)。臺灣股市技術分析實證：以隨機指標、相對強弱指標、指數平滑異同平均線指標及趨向指標為例。高雄應用科技大學人文與社會科學學刊，1(2)，119-133。