淡江大學覺生紀念圖書館 (TKU Library)
進階搜尋


下載電子全文限經由淡江IP使用) 
系統識別號 U0002-2707201210270500
中文論文名稱 應用馬可夫決策過程與遺傳演算法於台灣股市投資策略制訂
英文論文名稱 Using Markov Decision Process and Genetic Algorithms for Formulating Taiwan Stock Trading Strategies
校院名稱 淡江大學
系所名稱(中) 資訊管理學系碩士班
系所名稱(英) Department of Information Management
學年度 100
學期 2
出版年 101
研究生中文姓名 李明昇
研究生英文姓名 Ming-Sheng Lee
學號 697631421
學位類別 碩士
語文別 中文
口試日期 2012-05-26
論文頁數 60頁
口試委員 指導教授-張應華
委員-張昭憲
委員-陳穆臻
中文關鍵字 馬可夫決策過程  遺傳演算法  股市投資  擇時  最佳化 
英文關鍵字 Markov decision process  genetic algorithms  the stock investment  timing  optimization 
學科別分類 學科別社會科學管理學
學科別社會科學資訊科學
中文摘要 隨著低利率時代來臨,投資者為了追求較高的報酬率,開始把資金投入股票投資市場,然而股市行情變換迅速,真正獲利的投資者不多,只有在適當時機點進場交易的投資者才能從中獲利。ㄧ般投資者大多利用技術指標做為進場時機的依據,然而使用技術指標會有ㄧ些問題,例如技術指標的選擇、互相矛盾或類似等問題,導致ㄧ般投資人很難利用這些資訊來輔助股市投資決策。
本研究結合馬可夫決策過程與遺傳演算法,提出新的分析架構,建立一個股市投資策略制訂的決策支援系統。本研究利用馬可夫決策過程具有的預測特性和近期資料即時分析能力,利用馬可夫決策過程在短期資料優秀的分析能力,解析過去歷史資料,達到擇時效果,再結合遺傳演算法的特殊編碼方式與極佳搜尋能力,以字串編碼表達不同的投資策略,以搜尋能力來求解出最佳投資策略,達到選股和資金配置效果。在資金與手中持股不足時,可透過此模型具有的融資融券方式來完成交易。經實驗證實本模型可以得到較高的報酬。
英文摘要 With the low interest rate coming, investors start to buy stocks to get more rewards. However, the stock market varied rapidly, seldom investors can get excess returns when trade in the proper time. Most investors use technical indicators as a tool for market timing. However using technical indicators has some problems, such as the choice of technical indicators, conflicting or similar and other prolems. So most investors are difficult to use those informations to determine stock market investment decisions.
This research combines Markov decision process and genetic algorithms to propose a new analytical framework and to develop the decision support system for making the stock trading strategies. This paper uses the prediction characteristics and real-time analysis capabilities of the Markov decision process to do timing decision. Doing the stock selection and fund allocation by using the string encoding to express different investment strategies and the search capabilities to solve the best investment strategy. Besides, when investors have no sufficient money and stocks, the architecture of this research can complete the transaction by credit transactions. By the experiments, it can confirm that the model of this research can get higher reward.
論文目次 目錄
壹、 緒論 1
第一節、 研究背景與動機 1
第二節、 研究目的 2
貳、 文獻探討 3
第一節、 演化計算與股票投資組合 3
第二節、 馬可夫決策過程與股票投資組合 6
參、 研究架構 8
第一節、 進場訊號—累積報酬率之馬可夫決策過程 9
第二節、 買賣交易策略—隔日預期報酬率之馬可夫決策過程 11
第三節、 選股與資金配置(融資、融券)—遺傳演算法求解 12
第四節、 整合與交易過程 15
肆、 實驗分析 18
第一節、 一般遺傳演算法(SGA) 18
第二節、 馬可夫整合遺傳演算法 29
第三節、 綜合實驗評比 38
伍、 結論與未來展望 55
參考文獻 56

圖目錄
圖1 研究架構圖 9
圖2 累積報酬率狀態變數 10
圖3 隔日預期報酬率狀態變數 11
圖4 染色體編碼 13
圖5 交配 14
圖6 突變 14
圖7 進場訊號、買賣訊號與染色體資產配置(融資、融券) 16
圖8 SGA染色體交配示意圖 19
圖9 SGA突變示意圖 19
圖10 SGA交易策略示意圖 20
圖11 2003年月報酬率最高月份報酬率和適應值收斂圖 20
圖12 2003年月報酬率最低月份報酬率和適應值收斂圖 21
圖13 2004年月報酬率最高月份報酬率和適應值收斂圖 21
圖14 2004年月報酬率最低月份報酬率和適應值收斂圖 22
圖15 2005年月報酬率最高月份報酬率和適應值收斂圖 22
圖16 2005年月報酬率最低月份報酬率和適應值收斂圖 23
圖17 2006年月報酬率最高月份報酬率和適應值收斂圖 23
圖18 2006年月報酬率最低月份報酬率和適應值收斂圖 24
圖19 2007年月報酬率最高月份報酬率和適應值收斂圖 24
圖20 2007年月報酬率最低月份報酬率和適應值收斂圖 25
圖21 2008年月報酬率最高月份報酬率和適應值收斂圖 25
圖22 2008年月報酬率最低月份報酬率和適應值收斂圖 26
圖23 2009年月報酬率最高月份報酬率和適應值收斂圖 26
圖24 2009年月報酬率最低月份報酬率和適應值收斂圖 27
圖25 2010年月報酬率最高月份報酬率和適應值收斂圖 27
圖26 2010年月報酬率最低月份報酬率和適應值收斂圖 28
圖27 2011年月報酬率最高月份報酬率和適應值收斂圖 28
圖28 2011年月報酬率最低月份報酬率和適應值收斂圖 29
圖29 2003年月報酬率最高月份報酬率和適應值收斂圖 30
圖30 2003年月報酬率最低月份報酬率和適應值收斂圖 30
圖31 2004年月報酬率最高月份報酬率和適應值收斂圖 31
圖32 2004年月報酬率最低月份報酬率和適應值收斂圖 31
圖33 2005年月報酬率最高月份報酬率和適應值收斂圖 32
圖34 2005年月報酬率最低月份報酬率和適應值收斂圖 32
圖35 2006年月報酬率最高月份報酬率和適應值收斂圖 33
圖36 2006年月報酬率最低月份報酬率和適應值收斂圖 33
圖37 2007年月報酬率最高月份報酬率和適應值收斂圖 34
圖38 2007年月報酬率最低月份報酬率和適應值收斂圖 34
圖39 2008年月報酬率最高月份報酬率和適應值收斂圖 35
圖40 2008年月報酬率最低月份報酬率和適應值收斂圖 35
圖41 2009年月報酬率最高月份報酬率和適應值收斂圖 36
圖42 2009年月報酬率最低月份報酬率和適應值收斂圖 36
圖43 2010年月報酬率最高月份報酬率和適應值收斂圖 37
圖44 2010年月報酬率最低月份報酬率和適應值收斂圖 37
圖45 2011年月報酬率最高月份報酬率和適應值收斂圖 38
圖46 2011年月報酬率最低月份報酬率和適應值收斂圖 38
圖47 2003年實驗結果比較圖 39
圖48 2004年實驗結果比較圖 41
圖49 2005年實驗結果比較圖 42
圖50 2006年實驗結果比較圖 44
圖51 2007年實驗結果比較圖 45
圖52 2008年實驗結果比較圖 47
圖53 2009年實驗結果比較圖 48
圖54 2010年實驗結果比較圖 50
圖55 2011年實驗結果比較圖 51
圖56 半年的報酬率變化圖 53

表目錄
表1 累積報酬率移轉次數矩陣 10
表2 累積報酬率移轉機率矩陣 10
表3 隔日報酬率移轉次數矩陣 11
表4 隔日報酬率移轉機率矩陣 12
表5 台灣銀行公告定存利率表 15
表6 資金配置調整表 15
表7 SGA染色體編碼 18
表8 2003年1月~12月實驗比較表 39
表9 2003年執行時間與收斂代數統計表 39
表10 2004年1月~12月實驗比較表 40
表11 2004年執行時間與收斂代數統計表 41
表12 2005年1月~12月實驗比較表 42
表13 2005年執行時間與收斂代數統計表 42
表14 2006年1月~12月實驗比較表 43
表15 2006年執行時間與收斂代數統計表 44
表16 2007年1月~12月實驗比較表 45
表17 2007年執行時間與收斂代數統計表 46
表18 2008年1月~12月實驗比較表 46
表19 2008年執行時間與收斂代數統計表 47
表20 2009年1月~12月實驗比較表 48
表21 2009年執行時間與收斂代數統計表 48
表22 2010年1月~12月實驗比較表 49
表23 2010年執行時間與收斂代數統計表 50
表24 2011年1月~12月實驗比較表 51
表25 2011年執行時間與收斂代數統計表 51
表26 半年平均報酬率統計表 52
表27 半年平均收斂代數與平均執行時間統計表 54

參考文獻 [1] 江錦宗,〈應用馬可夫決策過程進行台灣股票投資分析之研究〉,東海大學工業工程與經營資訊研究所碩士論文,2002。
[2] 林師賢,〈組合型基金設計-組合編碼遺傳演算法之應用〉,銘傳應用統計資訊學系碩士論文,2008。
[3] 林典蓉,〈應用基因演算法與灰色決策建構擇股策略模型〉,朝陽科技大學財務金融系碩士論文,2008。
[4] 姚凱齡,〈整合限制滿足概念於遺傳演算法制定股票投資策略之研究〉,大同大學資訊經營研究所碩士論文,2008。
[5] 施和綸,〈多父代遺傳演算法於投資組合決策模型之分析研究〉,世新大學資訊管理研究所碩士論文,2011。
[6] 施志樹,〈以遺傳演算法為基礎考慮市場特徵之股票評價與動態資產配置架構〉,國立高雄應用科技大學金融資訊研究所碩士論文,2007。
[7] 詹松盛,〈應用馬可夫鏈進行台股與期貨間交易策略〉,國立中央大學財務金融研究所碩士在職專班論文,2004。
[8] 楊士賢,〈應用馬可夫決策過程進行台股期貨日內交易策略之研究〉,東海大學工業工程與經營資訊研究所碩士論文,2003。
[9] 楊靜榆,〈兩狀態下的國際資產配置-馬可夫轉換模型之應用〉,國立中央大學財務管理研究所碩士論文,2001。
[10] 鄭敦維,〈一個基植於遺傳演算法與模糊理論最佳化之支援向量機選股模型〉,國立高雄大學資訊工程研究所碩士論文,2011。
[11] 蔡明憲、俞淑惠與黃永祥,〈法人投資策略-以動態馬可夫模型分析〉,第五屆全國實證經濟學論文研討會,2004。
[12] Allen, F., Karjalainen, R., “Using genetic algorithms to and technical trading rules”, Journal of Financial Economics, vol. 51, no. 2, 1999, pp. 245-271.
[13] Bao, Y., “Stock market prediction model based on genetic algorithm and support vector regression”, Proceeding of the International Conference on Energy and Environmental Science, Singapore, 2011, pp. 4025-4029.
[14] Badawy, F.A., Abdelazim, H.Y. and Darwish, M.G., “Genetic Algorithms For Predicting The Egyptian Stock Market”, Proceedings of the International Conference on Information and Communications Technology, Cairo, 2005, pp. 109-122.
[15] Bermúdez, J. D., Segura, J. D., Vercher, E., “A multi-objective genetic algorithm for cardinality constrained fuzzy portfolio selection”, Fuzzy Sets and Systems, vol. 188, no. 2, 2012, pp. 16-26.
[16] Chang, T. J., Yang, S. C., and Chang, K. J., “Portfolio optimization problems in different risk measures using genetic algorithm”, Expert Systems with Applications, vol. 36, no. 7, 2009, pp. 10529-10537.
[17] Changchien, Y. W., Chen, Y. L., “Mining associative classification rules with stock trading data – A GA-based method”, Knowledge-Based Systems, vol. 23, no. 6, 2010, pp. 605–614.
[18] Chen, Y., Mabub, S. and Hirasawa, K., “Genetic relation algorithm with guided mutation for the large-scale portfolio optimization”, Expert Systems with Applications, vol. 38, no. 4, 2011, pp. 3353-3363.
[19] Chen, G., Chen, X., “A Hybrid of Adaptive Genetic Algorithm and Pattern Search for Stock Index Optimized Replicate”, Proceedings of Artificial Intelligence, Management Science and Electronic Commerce, Deng Leng, 2011, pp. 4912-4915.
[20] Cheng, C. H., Chen, T. L. and Wei, L. Y., “A hybrid model based on rough sets theory and genetic algorithms for stock price forecasting”, Information Sciences, vol. 180, no. 9, 2010, pp. 1610-1629.
[21] Cheung, L.W.K. “Use of runs statistics for pattern recognition in genomic DNA sequences”, Journal of Computational Biology, vol. 11, no. 1, 2004, pp. 107–124.
[22] Chun, Q., John, C. S. and Tang, “Foreign direct investment: A genetic algorithm approach”, Socio-Economic Planning Sciences, vol. 40, no. 2, 2006, pp. 143-155.
[23] Chiu, D. Y., Chian, S. Y., “Exploring stock market dynamism in multi-nations with genetic algorithm, support vector regression, and optimal technical analysis”, Proceedings of Sixth International Conference on Networked Computing and Advanced Information Management, Seoul, 2010, pp. 694-699.
[24] Dastkhan, H., Gharneh, N.S. and Golmakani, H.R., “A linguistic-based portfolio selection model using weighted max–min operator and hybrid genetic algorithm”, Expert Systems with Applications, vol. 38, 2011, pp. 11735-11743.
[25] Du, P., Luo, X., He, Z., Xie, L., “The Application of Genetic Algorithm-Radial Basis Function (GA-RBF) Neural Network in Stock Forecasting”, Proceedings of Control and Decision Conference, Xuzhou, 2010, pp. 1745-1748.
[26] Esfahanipour, A., Mousavi, S., “A genetic programming model to generate risk-adjusted technical trading rules in stock markets”, Expert Systems with Applications , vol. 38, no. 7, 2011, pp. 8438-8445.
[27] Fasanghari, M., Ali Montazer, G., “Design and implement of fuzzy expert system for Tehran Stock Exchange portfolio recommendation”, Expert Systems with Applications, vol. 37, no. 9, 2010, pp. 6138-6147.
[28] Fu, K., Xu, W., “Training Neural Network with Genetic Algorithms for Forecasting the Stock Price Index”, Proceedings of International Conference on Intelligent Processing Systems, Beijing, 1997, pp. 401-403.
[29] Gelman, S., Wilfling, B., “Markov-switching in target stocks during takeover bids”, Journal of Empirical Finance , vol.16, no. 5, 2009, pp. 745-758.
[30] Ghezzi, L., Piccardi, C., “Stock valuation along a Markov chain”, Applied Mathematics and Computation, vol. 141, no. 2-3, 2003, pp. 385–393.
[31] Gold, S. and Lebowitz, P., “Computerized Stock Screening Rules for Portfolio Selection”, Financial Service Review, vol.8, no. 8, 1999, pp. 61-70.
[32] Gorgulho, A., Neves, R. and Horta, N., “Applying a GA kernel on optimizing technical analysis rules for stock picking and portfolio composition”, Expert Systems with Applications, vol 38, 2011, pp. 14072-14085.
[33] Hassan, M.R., “A combination of hidden Markov model and fuzzy model for stock market forecasting”, Neurocomputing , vol. 72, no. 16-18, 2009, pp. 3439–3446.
[34] Hoklie and Zuhal, L.R., “Resolving Multi Objective Stock Portfolio Optimization Problem Using Genetic Algorithm”, Proceedings of the 2nd International Conference on the Computer and Automation Engineering, Singapore, 2010, pp. 40-44.
[35] Hsu, Y.T., Liu, M.C., Yeh, J. and Hung, H.F., “Forecasting the turning time of Stock Market based on Markov-Fourier Grey Model”, Expert Systems with Applications, Vol 36, no. 4, 2009, pp. 8597-8603.
[36] Huang, C.F., “A hybrid stock selection model using genetic algorithms and support vector regression”, Applied Soft Computing, vol. 12, no. 2, 2012, pp. 807-818.
[37] Huang, S. C., Wu, T. K., “Integrating GA-based time-scale feature extractions with SVMs for stock index forecasting”, Expert Systems with Applications, vol 35, no. 4, 2008, pp. 2080–2088.
[38] Jang, G.S., Lai, F. and Parng, T.M., “Intelligent Stock Trading Decision Support System Using Dual Adaptive-Structure Neural Networks”, Journal of Information Science and Engineering, vol. 9, no. 2, 1993, pp. 271-297.
[39] Jiang, Rui and Szeto, K. Y., “Discovering investment strategies in portfolio management: A genetic algorithm approach”, Proceedings of 9th International Conference on Neural Information Processing, Singapore, 2002, pp. 1206-1210.
[40] Kara, Y., Boyacioglu, M.C. and Baykan, O.K., “Predicting direction of stock price index movement using artificial neural networks and support vector machines: The sample of the Istanbul Stock Exchange”, Expert Systems with Applications, vol. 38, no. 5, 2011, pp. 5311-5319.
[41] Khan, A.U., Bandopadhyaya, T. K. and Sharma, S., “Genetic Algorithm Based Backpropagation Neural Network Performs better than Backpropagation Neural Network in Stock Rates Prediction”, International Journal of Computer Science and Network Security, vol. 8, no. 7, 2008, pp. 162-166.
[42] Kim, H.J., Shin, K.S., “A hybrid approach based on neural networks and genetic algorithms for detecing temporal patterns in stock markets”, Applied Soft Computing, vol. 7, no. 2, 2007, pp. 569-576.
[43] Kimoto, T., Asakawa, K., Yoda, M. and Takeoka, M., “Stock Market Prediction System with Modular Neural Networks”, In Proceeding of the International Joint Conference on Neural Networks, San Diego, 1990, pp. 1-6.
[44] Ko, P.C., Lin, P.C. and Tsai Y.T., “A Nonlinear Stock Valuation Using a Hybrid Model of Genetic Algorithm and Cubic Spline”, Proceedings of the Conference on Innovative Computing, Information and Control, Kumamoto, 2007, pp. 210-213.
[45] Korczak, J., Roger, P., “Stock timing using genetic algorithms”, Applied Stochastic Models in Business and Industry, vol. 18, no. 2, 2002, pp. 121-134.
[46] Laura, N., “Fitting the control parameters of a genetic algorithm: An application to technical trading systems design”, European Journal of Operational Research, vol. 179, pp. 847-868.
[47] Lazo, J. G., Vellasco, B. R., and Pacheco, A. C., "A Hybrid Genetic-Neural System for Portfolio Selection and Management, Proceedings of Sixth International Conference on Engineering Applications of Neural Networks", Kingston Upon Thames, 2000.
[48] Leu, Y., Chiu, T.I., “An Effective Stock Portfolio trading Strategy using Genetic Algorithms and Weighted Fuzzy Time Series”, Proceedings of Nano, Information Technology and Reliability, Macao, 2011, pp. 70-75.
[49] Li, J., Tsang, E.P.K., “Investment decision-making using FGP: a case study”, CEC Proceedings of the Congress on Evolutionary Computation, Brisbane, 1999, pp. 14-21.
[50] Oh, K. J., Kim, T. Y., Min, S. H. and Lee, H. Y., “Portfolio algorithm based on portfolio beta using genetic algorithm”, Expert Systems with Applications, vol. 30, no. 3, 2006, pp. 522-534.
[51] Orito, Y. and Yamazaki, G., “Index Fund Portfolio Selection by Using GA”, Proceedings of the Fourth International Conference on Computational Intelligence and Multimedia Applications, Yokusika, 2001, pp. 118-122.
[52] NG, H.S., LAM, K.P. and LAM S.S., “Incremental Genetic Fuzzy Expert Trading System For Derivatives Market Timing”, Proceeding of the Computational Intelligence for Financial Engineering, Hong Kong, 2003, pp. 421-427.
[53] Papadamou, S., Stephanides, G., “Improving technical trading systems by using a new MATLAB-based genetic algorithm procedure”, Mathematical and Computer Modelling, vol. 46, 2007, pp. 189-197.
[54] Rafaely, B. and Bennell, J. A., “Optimisation of FTSE100 tracker funds: Acomparison of genetic algorithms and quadratic programming”, ManagerialFinance, vol.32, no. 6, 2006, pp. 477-492.
[55] Shoaf, J. and Foster, J. A., “The Efficient Set GA for Stock Portfolio”, Proceedings of the IEEE International Conference on Evolutionary Computation, Alaska, 1998, pp. 354-359.
[56] Soleimani, H., Golmakani, H. R. and Salimi, M. H., “Markowitz-based portfolio selection with minimum transaction lots, cardinality constraints and regarding sector capitalization using genetic algorithm”, Expert Systems with Applications, vol. 36, no. 3, 2009, pp. 5058-5063.
[57] Wang, J.Z., Wang, J.J., Zhang, Z.G., Guo, S.P., “Forecasting stock indices with back propagation neural network”, Expert Systems with Applications, vol. 38, no. 11, 2011, pp. 14346-14355.
[58] Wang, Y.F., Cheng, S., Hsu, M.H., “Incorporating the Markov chain concept into fuzzy stochastic prediction of stock indexes”, Applied Soft Computing, vol. 10, no. 2, 2010, pp. 613-617.
[59] Shen, W., Xing, M., “Stock Index Forecast with Back Propagation Neural Network Optimized by Genetic Algorithm”, Proceedings of the Second International Conference on Information and Computing Science, Manchester, 2009, pp. 376-379.
[60] Versace, M., Bhatt, R., Hinds, O., Shiffer, M., “Predicting the exchange traded fund DIA with a combination of genetic algorithms and neural networks”, Expert Systems with Applications, vol. 27, 2004, pp. 417-425.
[61] Xie, H., Anreae, P., Zhang, M., Warren, P., “Learning models for english speech recognition”, Proceedings of the 27th Conference on Australasian Computer Science, Darlinghurst, 2004, pp. 323-329.
[62] Yang ,Y., Liu, G., Zhang, Z., “Stock market trend prediction based on neural networks, multiresolution analysis and dynamical reconstruction”, Proceedings of the IEEE/IAFE/INFORMS Conference on Computational Intelligence for Financial Engineering, New York, 2000, pp. 155 – 156.
論文使用權限
  • 同意紙本無償授權給館內讀者為學術之目的重製使用,於2017-07-31公開。
  • 同意授權瀏覽/列印電子全文服務,於2017-07-31起公開。


  • 若您有任何疑問,請與我們聯絡!
    圖書館: 請來電 (02)2621-5656 轉 2281 或 來信