• 沒有找到結果。

以基因進化方法最佳化買賣時機之研究 沈承儒、李俊德

N/A
N/A
Protected

Academic year: 2022

Share "以基因進化方法最佳化買賣時機之研究 沈承儒、李俊德"

Copied!
2
0
0

加載中.... (立即查看全文)

全文

(1)

以基因進化方法最佳化買賣時機之研究 沈承儒、李俊德

E-mail: 9806144@mail.dyu.edu.tw

摘 要

本研究以台灣加權指數(TAIEX)為研究對象,並採用曾家翔(2008)與黃婉君(2009)研究中經由類神經網路預測系統訓練過的 幾組較佳準確率的綜合指標當作初始輸入變數測試,並加上量價關係指標,再搭配基因程式規劃來分析大量的歷史資料,

來判別股市未來的走勢及轉折點,確實掌握買賣點的時機。

基因程式規劃採用的適應函數分別為最大報酬導向及趨勢獲利導向,來進行相關測試。探討GP(最大報酬)、GP(趨勢獲利)

、買進持有策略以及類神經網路預測系統四種策略的報酬率比較。結果顯示,以GP(趨勢獲利)獲得最佳報酬,其次為GP(

最大報酬),然後依序為類神經網路預測系統與買進持有策略。本研究發現,利用GP(最大報酬)的訓練方式,常常會因為股 市整盤或是小震盪,導致系統的誤判,而降低報酬率,而GP(趨勢獲利)的訓練方式,利用設定趨勢目標值的方式來訓練系 統,驗證結果,無論是轉折點或趨勢大致上皆能反應實際的股價走勢,同時也獲得較大的報酬率。本研究的結果並不認同 效率市場假說

關鍵詞 : 基因程式規劃、最大報酬導向、趨勢獲利導向、效率市場假說 目錄

中文摘要 ...................... iii 英文摘要 ...................... iv 誌謝辭  ...................... v 內容目錄 ...................... vi 表目錄  ...................... viii 圖目錄 ...................... x 第一章  緒論.................... 1 第一節  研究背景與動機............. 1

  第二節  研究目的................... 3 第三節  研究流程................ 4

第四節  研究範圍................ 5 第五節  論文架構................ 6 第二章  文獻探討.................. 7   第一節  效率市場假說.............. 7 第二節  基本分析與技術分析........... 9 第三節 類神經網路............... 18 第四節 基因程式規劃.............. 20 第五節 國內外文獻探討............. 22

第三章  研究方法.................. 35 第一節  實驗步驟................ 35 第二節  變數與資料建置............. 37 第三節  基因程式規劃建置............ 38 第四節  基因程式規劃的訓練與驗證........ 40 第四章  實證結果與分析............... 41 第一節  交易策略................ 42 第二節  指標組合挑選.............. 41 第三節  基因程式規劃與類神經網路比較........ 46 第四節  拆解指標組合比較............. 48 第五節  四種投資策略比較............ 52 第五章  結論與建議................. 59 第一節  研究結論................ 59

(2)

第二節  研究貢獻................ 60 第三節  未來研究方向.............. 61 參考文獻 ...................... 63 參考文獻

Fama, E. F. (1970). Efficient capital markets. A review of theory and empirical work. Journal of Finance, 25(2), 383-417.Fifield, S. G. M., Power, D.M., & Donald Sinclair, C. (2005). An analysis of trading strategies in eleven European stock markets. European Journal of Finance, 11(6), 531-548.Gunasekarage, A., & Power, D. M.(2001). The profitability of moving average trading rules in South Asian stock markets. Emerging Markets Review, 2(3), 17-33.Jean, Y. P., Patrick, S., & Maxime, V.(2004). Generating trading rules on the stock markets with genetic programming, Computers and Operations Research, 31(7), 1033-1047.Jiah, S. C., Chia, L. C., Jia, L. H., & Yao, T. L.(2008). Dynamic proportion portfolio insurance using genetic programming with principal component analysis, Expert Systems with Applications, 35(4), 273-278.Koza, J. R. (1992).

Genetic programming: On the programming of computers by means of natural selection. London: MIT-Press.Kwon, K. Y., & Kish, R. J. (2002).

Technical trading strategies and return predictability: NYSE. Applied Financial Economics, 12(9), 639-653.Lee, A. B., & Seshadri, N.(2003).

GP-evolved technical trading rules can outperform buy and hold. Financial Applications of Genetic Programming, 4(2), 2-3.Lee, C. T., & Chen, Y.

P. (2007). The efficacy of neural networks and simple technical indicators in predicting stock markets, Proceedings of the 2007 International Conference on Convergence Information Technology(pp.2292-2297), Singapore:University of Singapore.Levy, Robert A. (1967). Relative strength as a criterion for investment selection. Journal of Finance, 22(3), 95-610Liad, W. (2003). Stock portfolio evaluation: An application of

genetic-programming-based technical analysis. Genetic Algorithms and Genetic Programming, 4(5), 3-4.Malkiel, B. G. (1999). A random walk down Wall Street (7th ed). New York: W. W. Norton & Company: London.Marshall, B. R., Young, M. R., & Rose, L.C. (2006). Candlestick technical trading strategies: Can they create value for investors? Journal of Banking & Finance, 30(4), 2303-2323.Pring, M. J. (1985). Technical analysis explained. (2nd ed.), New York: McGraw-Hill.Shmilovici, A., Alon-Brimer, Y., & Hauser, S. (2003). Using a stochastic complexity measure to check the efficient market hypothesis. Computational Economics, 22(2), 273-284.Szakmary, A., Davidson, W. N., & Schwarzy, T. V. (1999).

Filter tests in Nasdaq Stocks. Finance Review, 34(4), 34-70.Tsang, E. P. K., & Li, J. (1999). Improving technical analysis predictions: an application of genetic programming. Proceedings of the florida artificial intelligence research symposium, Florida Artificial Intelligence Research Symposium, 1-13.

參考文獻

相關文件

使用 AdaBoost 之臺股指數期貨當沖交易系統 Using AdaBoost for Taiwan Stock Index Future Intra-.. day

In this paper, by using Takagi and Sugeno (T-S) fuzzy dynamic model, the H 1 output feedback control design problems for nonlinear stochastic systems with state- dependent noise,

This bioinformatic machine is a PC cluster structure using special hardware to accelerate dynamic programming, genetic algorithm and data mining algorithm.. In this machine,

介面最佳化之資料探勘模組是利用 Apriori 演算法探勘出操作者操作介面之 關聯式法則,而後以法則的型態儲存於介面最佳化知識庫中。當有

This thesis will focus on the research for the affection of trading trend to internationalization, globlization and the Acting role and influence on high tech field, the change

(2004), "Waiting Strategies for the Dynamic Pickup and Delivery Problem with Time Window", Transportation Research Part B, Vol. Odoni (1995),"Stochastic and Dynamic

Keywords: light guide plate, stamper, etching process, Taguchi orthogonal array, back-propagation neural networks, genetic algorithms, analysis of variance, particle

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