若台灣股票市場普遍存在弱效率市場現象，投資人即可透過擇時、選股操作方式來獲取超額報酬。本研究運用遺傳演算法(Genetic Algorithms, GA)來產生指標的組合變化，適應函數則以迴歸分析(Regression Analysis)來計算及演化，成功的篩選出與股價具有顯著關聯之關鍵指標，再評估個股在基本面表現的相對強弱勢，進而提昇選股準確度及投資績效，最後，並結合投資組合報酬率、風險(Risk)、風險值(VaR)，以及夏普指標(Sharpe Ratio)等，來評估投資組合優劣，以尋求最佳投資組合及其選股操作模式。
研究樣本為民國88年至94年間，共計7年（84個月）全部上市個股（近700檔股票）之月資料及季資料，產生出共計1440種投資組合，由實驗結果顯示市場存在反應不足現象。從實驗參數組合之投資報酬發現，台灣上市股票市場效率具有1∼2月的落差(D)，而且指標與股價差距月數(G)1∼2個月的投資績效最佳，顯示台灣股票市場由弱效率市場朝效率市場趨勢移動。在進行投資操作時，採用具有產業權重之投資組合決策選股模式的準確性最佳，意即產業權重表現優於個股權重，可創造較高的投資報酬。
依據本實驗挑選L60-G1-SW2-W2-D1-S2組合來進行各式敏感度測試顯示，60個月的迴歸分析計算因資訊較完整揭露，而依此模擬所得到的關鍵指標投入市場的績效相較於36個月的迴歸分析計算的投資績效更為優異。再者，本實驗設計所篩選出之投資組合在空頭市場相對抗跌，多頭市場時反彈力道強勁，而盤整期更維持穩定高報酬率，投資績效亦較同期國內股票型基金表現更佳，顯示本研究投資選股模式，在結合市場效率因素所產生之投資組合，相對具有更高的投資績效。

If there exists a weak efficiency phenomenon in stock market of Taiwan, investors can obtain excessive remuneration through timing and selecting stock operation. This research adopts the model of ' Genetic Algorithms ' (GA) to produce the association of the financial indicator changes, and the fitness function in ' Regression Analysis '. It succeeds in finding key financial indicator that is obviously relative to the stock price change. And this model can assess the relatively strong or weak tendency that the stock displays on the basic side effectively, thus it will promote the accuracy of selecting stocks and investment performance. Finally, the research model combines the rate of returns of portfolio, Risk, Value at Risk (VaR), and Sharpe Ratio, etc., to assess the quality of the portfolio, and find out the best portfolio and the operation mode of choosing the stock.
The study samples are listing shares ( Nearly 700 stocks) from monthly and quarterly data of 7 years(1999 ~ 2005, Total 84 months). There are 1440 kinds of portfolio in all experiments. The experimental result shows that the market has insufficient response phenomenon. From the investment remuneration of the experiment parameters, we find that the market efficiency in Taiwan delays (D) from one month to two months. The investment performance is the best when the indicator and stock price are in 1 or 2 months gap (G). It also shows that the stock market of Taiwan is moving from weak efficiency market to the efficiency market. While investing, we can create higher investment remuneration using the accuracy of the portfolio decision with industry's weight selects stocks, meaning the result of the industry’s weight is superior to the stock’s weight of the stock).
According to this experiment( we select a portfolio (L60-G1-SW2-W2-D1-S2) to test on various types of susceptibilities), the result shows the investment performance of the regression analysis in 60 months ,which reveals more intact information, is superior to the one in 36 months. Moreover, the portfolio that experimental design filtered is relatively difficult to drop deeply in the bear market, rebounds powerfully in the bull market, and maintains the steady high rate of returns at other time. The performance of investment is also better than the domestic equity fund. This portfolio which combines investment model of selecting stocks and the factor of the market efficiency has higher investment performances relatively.

1.江吉雄，遺傳演算法於股市選股與擇時策略之研究，中央大學資訊管理研究所碩士論文，2002。
2.何鴻聖，自我組織神經網路在選股策略的應用，國立東華大學國際經濟研究所碩士論文，2004。
3.林廷樂，臺灣股市價與量關係之實證研究－以電子股為例，國立中興大學企業管理研究所碩士論文，1998。
4.林承穆，企業經營績效評估與投資組合績效之探討-以上市電子資訊公司為例，國立東華大學企業管理研究所碩士論文，2004。
5.林萍珍，遺傳演算法在使用者導向的投資組合選擇之應用，國立中央大學資訊管理研究所碩士論文，1998。
6.林鴻達，市場效率性之分析—以STAR模型為例，國立中山大學中山學術研究所碩士論文，2006。
7.孫院明，演化式計算在多階段投資決策模型建構之評估與應用，輔仁大學資訊管理研究所碩士論文，2007。
8.康登傑，台指選擇權市場效率性之研究，南華大學財務管理研究所碩士論文，2003。
9.侯佳利，組合編碼遺傳演算法於投資組合及資金分配之應用，國立中央大學資訊管理研究所碩士論文，2001。
10.陳宗益，利用總經變數掌握台股趨勢，台大會計學研究所未出版碩士論文，2001。
11.陳柏年，應用遺傳演算法於財務指標選股策略之探討，中央大學資訊管理研究所碩士論文，2000。
12.陳信宏，投資組合決策最佳化與績效指標之研究，國立中山大學企業管理學系博士論文，2004。
13.許和鈞、劉永欽，台灣地區股票市場價量之線性與非線性Granger因果關係之研究，證券市場發展季刊，1996，頁23-49。
14.張雅惠，應用風險值評估共同基金之績效，國立政治大學金融研究所碩士論文，2000。
15.黃嘉斌譯，Benjamin Graham著，證券分析，寰宇出版社，台北，91 年。
16.黃慶光，台灣股價指數反向操作策略及價量關係分析，國立中正大學企業管理研究所碩士論文，2001。
17.楊千霈，遺傳演算法在整合式價值投資策略之應用，輔仁大學資訊管理研究所碩士論文，2003。
18.銘傳大學財務金融研究中心編著，投資分析+ Matlab應用，台北：全華科技圖書公司，2004。
19.蒲建亨，整合VaR 法之衡量與驗證-以台灣金融市場投資組合為例，政治大學國際貿易研究所碩士論文，2000。
20.蔡劼麟，台灣股票市場價格動量與周轉率之週期循環研究，銘傳大學金融研究所碩士論文，1999。
21.蔡俊生，投資組合之風險值衡量，世新大學財務金融研究所碩士論文，2004。
22.顏志杰，遺傳演算法在股票投資組合風險值模型建構之應用－以臺灣50指數成份股票為例，輔仁大學資訊管理研究所碩士論文，2005。

1.Alexander, C.O. and Leigh, C.T., On the Covariance Matrices Used in Value at Risk Model, The Journal of Derivatives, Spring 1997, pp. 50-62.
2.Basle Committee on Banking Supervision, Amendment to the capital accord to incorporate market risks, Basle: Bank for International Settlement, 1996.
3.Bradley E., Bootstrap Methods: Another Look at the Jackknife, The Annals of Statistics, 7 (1), 1979, pp. 1–26.
4.De Raaji, G. and Raunig, B., Value at Risk - Evaluierung verschiedener Verfahren, OeNB-Berichte und Studien, Heft 4, 1998, pp. 84-98.
5.Dowd, K., Beyond Value at Risk: The new science of risk management, John Wiley & Sons Ltd, 1998.
6.Fama, E. F., Efficient capital markets：A review of theory and empirical work, Journal of Finance Vol. XXV, No.2, May 1970, pp. 383-417.
7.Fama, E.F., and French, K., The cross-section of expected stock returns, Journal of Finance, 47, 1992, pp. 427-465.
8.Hendricks, D., Evaluation of Value at Risk Models Using Historical Data, Economics Policy Review, April 1996, Vol.2, No.1, pp. 39-69.
9.Holland, J. H., Adaptation in Natural and Artificial Systems, University of Michigan Press, 1975.
10.Jackson, P., Maude, D. J., and Perraudin, W., Bank Capital and Value at Risk, The Journal of Derivatives, fall 1997.
11.Jegadeesh, N., and Titman, S., Returns to buying winners and selling losers, Implications for stock market efficiency, Journal of Finance 48, 1993, pp. 65-91.
12.Jensen, M. C., The Performance of Mutual Funds in the Period 1945-64, Journal of Finance, 1968 Vol. 23, pp. 389-416.
13.Jorion, P., Value at Risk: The New Benchmark for Controlling Market Risk, Mc-Graw-Hill Companies, Irwin Professional Publishing, 1997.
14.Lee, C. M. C., and Swaminathan, B., Price momentum and trading volume, Working paper, Cornell University, August 29, 1999。
15.Linter, J., The valuation of risk assets and the selection of risky investments in stock portfolios and capital budgets, The Review of Economics and Statistics, 47(1), 1965, pp. 13-37.
16.Markowitz, H. M., Portfolio selection, The Journal of Finance, 7, 1952, pp. 71-91.
17.Morgan, J. P., Riskmetrics Technical Document, Fourth Edition, 1996.
18.Moskowitz, T. J. and Grinblatt, M., Do Industries explain momentum, Journal of Finance 54, 1999, pp. 1249-1290.
19.Mossin, J., Equilibrium in A Capital Asset Market, Econometric, Oct, 1966, pp. 768-783.
20.Nicholson, F., Pricing-Earnings Ratios, Financial Analyst Journal, Aug 1960, pp.43-45.
21.Sharpe, W. F., Capital Asset Prices: A Theory of Market Equilibrium under　Condition of Risk, Journal of Finance, Vol.19, No. 3, Sep., 1964, pp. 425-442.
22.Sharpe, W. F., Mutual Fund Performance, Journal of Business, 1966, pp. 119-138.
23.Sharpe, W. F., The Sharpe Ratio, The Journal of Portfolio Management, 21, 1994, pp. 49-58.
24.Terasvirta, T. and Anderson, H. M., Characterizing Nonlinearities in Business Cycles Using Smooth Transition Autoregressive Models. Journal of Applied Econometrics, 1992, 7 (S), pp. 119-136.