Basic Search / Detailed Display

Author: 詹博凱
Po-Kai Chan
Thesis Title: 運用基因演算法以輔助股票市場投資人判斷進場時機之研究
Trading Timing Strategy Evaluation on Stock Market Using Genetic Algorithm
Advisor: 羅乃維
Nai-Wei Lo
Committee: 林伯慎
Bor-Shen Lin
楊屯山
Tun-Shan Yang
Degree: 碩士
Master
Department: 管理學院 - 資訊管理系
Department of Information Management
Thesis Publication Year: 2007
Graduation Academic Year: 95
Language: 英文
Pages: 42
Keywords (in Chinese): 基因演算法技術分析股票市場
Keywords (in other languages): Keywords:Genetic Algorithm, Technical Analysis, Stock Market
Reference times: Clicks: 511Downloads: 10
Share:
School Collection Retrieve National Library Collection Retrieve Error Report
  • 由於投資股票的高報酬率,因此它一直是一個熱門的投資標的。不過伴隨著高報酬率而來的高風險,一般投資人需要更多的資訊及交易策略來幫助決策。技術分析是一個重要的分析工具,它根據過去的股價,相關資訊和走勢圖來預測未來的股價走勢。而為了驗證技術指標的有效性,本研究會選取一些指標來進行測試。
    在本研究中我們利用基因演算法去決定技術指標的組合和每個指標的權重值。而我們也會建構一個交易系統來模擬股市的真實買賣,這個系統會有幾種不同的交易策略可以選擇。道瓊工業指數成份股中的IBM, Intel和Wal-Mart是我們的研究對象,測試的區間是在2002和2004之間。
    根據實驗發現除了Wal-Mart外的報酬率結果幾乎都能顯著的擊敗買入持有策略(buy and hold)。此外使用多口交易(multiple transaction trading)策略比單口交易(single transaction trading) 策略風險低;使用買賣訊號相抵(signal collision cancellation)策略的平均報酬優於買賣訊號不相抵(signal collision recognition)策略。另一方面我們還測試不同時間長度訓練期,並推論出當訓練期長度訂為一年與一個月時的結果最為穩健。最後實驗在有考慮交易成本的情形下統計出平均勝過買入持有策略大約17%和62%之間,因此我們能相信本研究提出一個好的方法去預測股票交易。


    Because of the high return rate, stock is always one of the popular investment targets. Considering the high level of risk based on high return rate, investors need more information and investment strategies to make a decision when trading stock.
    Technical analysis is an important tool which depends on the past stock price, volume data and different charts to predict the fluctuation of stock market. In order to confirm the effectiveness of technical indexes, we select some technical rules to predict the trend on stock market.
    In our research, we utilize genetic algorithm to decide the combination of technical rules and their weights. Then we proposed a trading system, which can choose different trading strategies to simulate the stock that investors buy or sell. IBM, Intel and Wal-Mart are investment targets within Dow Jones Industrial Index and the testing period is between 2001 and 2004.
    As the result, we found that in spite of the results of Wal-Mart our experiments can always beat the buy and hold benchmark method. In addition, using multiple transaction trading mechanism had a lower risk than single transaction trading mechanism and signal collision cancellation mechanism has better return than signal collision recognition mechanism. We also tested the different lengths of learning period and deduced the robust result when setting the length as one year and one month. Finally, our results after concerning transaction cost still exceeds the return rate of buy and hold method between 17% and 62%. Hence it is believed that our research provided a good strategy method in stock trading.

    中文摘要 I Abstract II 誌謝 III Contents IV Chart Contents VI Table Contents VII Chapter 1 Introduction 1 1.1 Background and motivation 1 1.2 Objective 2 1.3 Outline of the thesis 3 Chapter 2 Related works 4 2.1 Theory in stock market 4 2.2 Genetic algorithm 5 2.3 Related works by using GA in stock market 8 Chapter 3 Research Method 10 3.1 Architecture and process description 10 3.2 Genetic algorithm module 13 3.2.1 The format of chromosome 13 3.2.2 Fitness function 14 3.2.3 The process of genetic algorithm module 16 3.3 Trading signal generation module 18 3.4 Trading simulation module 19 3.4.1 Assumption 19 3.4.2 Trading strategy 20 Chapter 4 Empirical studies 27 4.1 Experimental environment and setting 27 4.2 Experiments results 28 Chapter 5 Conclusion and future work 36 Bibliography 38 Appendix A All strategy results 41

    [1]. Fama, Eugene F., “The Behavior of Stock Market Prices,” Journal of Business, pp.285-299, January 1965
    [2]. Fama, Eugene F., “Efficient Capital Markets: A Review of Theory and Empirical Work,” Journal of Finance, Vol. 25, pp.383-417, May 1970
    [3]. J. Kingdon and K. Feldman. “Genetic algorithm and application to finance.” Applied Mathematical Finance 2, pp.89-116, 1995.
    [4]. Sam Mahfoud and Ganesh Mani. “Financial Forecasting using Genetic Algorithm.” Applied Artificial Intelligence 10, pp.543-565, 1996.
    [5]. Franklin Allen and Risto Karjalainen. “Using genetic algorithms to find technical trading rules.” Journal of Financial Economics 51, 245-271, 1999.
    [6]. Georges R. Harik, Fernando G. Lobo and David E. Goldberg.” The Compact Genetic Algorithm.” IEEE Transactions on Evolutionary Computation. Vol. 3, No. 4, 287-297, November 1999.
    [7]. K. C. Lam, Tie Song Hu, Thomas Ng, R. K. K. Yuen, S. M. Lo and Conrad T. C. Wong. “Using an adaptive genetic algorithm to improve construction finance decisions. Engineering,” Construction and Architectural Management. 8-1, 31–45, 2001.
    [8]. Thomas K. L. Tong, C. M. Tam and Albert P. C. Chan. “Genetic algorithm optimization in building portfolio management. Construction Management and Economics 19, 601-609, 2001.
    [9]. J. Korczak and P. Roger. “Stock timing using genetic algorithm.” Applied Stochastic Models in Business and Industry. 18:121-134, 2002.
    [10]. Rui Jiang and K. Y. Szeto. “Discovering investment strategies in portfolio management: a genetic algorithm approach.” Proceedings of the 9th International Conference on Neural Information Processing. Vol. 3, 1206-1210, 2002.
    [11]. Rui Jiang and K. Y. Szeto. “Extraction of Investment Strategies based on Moving Averages: A Genetic Algorithm Approach.” IEEE 0-7803-7654-4/03, 403-410, 2003
    [12]. Badawy, F.A. Abdelazim, H.Y. and Darwish, M.G. “Genetic Algorithms for Predicting the Egyptian Stock Market” Information and Communications Technology , 2005. Enabling Technologies for the New Knowledge Society: ITI 3rd International Conference on
    Publication Date: 5-6 Dec. 2005
    [13]. Orito, Y. and Yamazaki, G. "Index fund portfolio selection by using GA"
    Computational Intelligence and Multimedia Applications, 2001. ICCIMA 2001. Proceedings. Fourth International Conference on Publication Date: 2001 On page(s): 118-122
    [14]. Yukiko Orito Hisashi Yamamoto and Genji Yamazaki "Index fund selections with genetic algorithms and heuristic classifications" Computers and Industrial Engineering Volume 45 , Issue 1 (June 2003) Pages: 97 - 109 Year of Publication: 2003
    [15]. Kyong Joo Oh Tae Yoon Kim Sung-Hwan Min and Hyoung Yong Lee "Portfolio algorithm based on portfolio beta using genetic algorithm" ScienceDirect Volume 30,Issue 3,April 2006, Pages 527-534
    [16]. Hayward, S. "setting up performance surface of an artificial neural network with genetic algorithm optimization in search of an accurate and profitable prediction for stock trading" Evolutionary Computation, 2004. CEC2004. Congress on Publication Date: 19-23 June 2004 Volume: 1, On page(s): 948- 954 Vol.1
    [17]. Kyong Joo Oh Tae Yoon Kim and Sungky Min "Using genetic algorithm to support portfolio optimization index fund management" ScienceDirect Volume 28,lssue 2 February 2005, Pages 371-379
    [18]. Yusen Xia, Baoding Liu, Shouyang Wang, K.K. Lai "A model for portfolio selection with order of expected returns" Computers & Operations Research 27 (2000) 409-422
    [19]. Baba, N. Kawachi, T. Nomura, T. and Sakatani, Y. "Utilization of NNs and GAs for improving the traditional technical analysis in the financial market" SICE 2004 Annual Conference Publication Date: 4-6 Aug. 2004 Volume: 2, On page(s): 1409- 1412 vol. 2
    [20]. An-Tsan Tsai “A Study of Applying Genetic Algorithm to Decide the Timing of Trading Stocks” 2005

    QR CODE