摘要
本研究利用Markowitiz 所提出的平均變異數模型以及人工智慧裡的基因演算法，來建構最佳化權重的基金投資組合。有別於過去的研究直接採用所有的投資組合作樣本，本研究為了更符合實際的投資狀況，在給定報酬下求最小風險及給定風險下求最大報酬的兩種情境，挑選出績效優異的前百分之三、前百分之五、前百分之十、前百分之十五及前百分之二十的投資組合做為下一期的投資，為了更客觀的指出績效較佳的投資組合具有較好的績效及績效持續性，本研究另挑選出績效較差的前百分之三、前百分之五、前百分之十、前百分之十五及前百分之二十，評估其績效持續性及績效差異。並利用MSCI 全球指數、S&P500 以及平均權重基金投資組合來比較其績效的優異。
受限於平均變異數模型要求的假設，例如:常態分配，造成大部分過去研究顯示基因演算法的績效優於平均變異數模型。本研究透過擴大樣本藉選定十七檔富蘭克林基金及十七檔富達基金分別共選出360檔及288檔組合型基金，進一步探討基因演算法所建構的基金投資組合是否還能優於平均變異數模型。
本研究發現:
一、 在報酬最大操作的績效表現優於風險最小下的績效表現。
二、 在大部分的情況下，平均變異數模型的績效顯著優於人工基因演算法。
三、 在平均變異數模型及人工基因演算法都顯示投資組合具有短期的績效持續性。透過增加投資組合數，可以提升績效持續性，然而本研究發現將投資組合增加至百分二十區間，可達較佳的績效持續性。

ABSTRACT
The study applies the Mean-Variance Model (MV) proposed by Markowitz and the Genetic Algorithms (GA) developed from artificial intelligence to construct optimal-weighted simulated fund portfolios. The main difference between this thesis and past studies is that we do not invest all portfolios; instead, we only choose the past top performance portfolios including three percent, five percent, ten percent, fifteen percent and twenty percent of all portfolio which is more rational, since investors might only want to choose past top percent of portfolio performing better due to expectation of continuing higher performance. To be more objective to evidence top performance portfolios have better performance, the study chooses the worse performance portfolios including three percent, five percent, ten percent, fifteen percent and twenty percent of all portfolio to examine whether there exists performance difference between portfolio invested based on past top and worse performance portfolios. The study also compares the performance of MV and GA with that of MSCI, S&P500 and Equally Weighted portfolio. Since there is the limitation required from the Markowitz model such as normal distribution of target asset, most prior researches demonstrate that the Genetic Algorithms outperforms the Mean-Variance Model. We proceed to examine whether the Genetic Algorithms can perform better than the Mean-Variance Model by examining funds portfolio based on 360 Franklin and 288 Fidelity funds portfolio.
There are several findings. First, the performance of the Mean-Variance Model and the Genetic Algorithms under maximizing return for a given risk is better than that under minimizing risk for a given return. Second, in most situations, the Mean-Variance Model outperforms the Genetic Algorithms. Finally, the result presents that the Mean-Variance Model and the Genetic Algorithms can improve performance persistence by increasing portfolios. Nevertheless, the phenomenon of performance persistence becomes better when the size of portfolio ranges in twenty percent.

Reference
Abiyev, R. H. and M. Menekay, (2007),“Fuzzy portfolio selection using Genetic Algorithms”, Soft Computing - A Fusion of Foundations, Methodologies & Applications, Vol. 11 Issue 12, 1157-1163.
Adler, T. and M. Kritzman, (2007),“Mean–variance versus full-scale optimization: In and out of sample”, Journal of Asset Management, Vol. 7 Issue 5, 302-311.
Allen, F. and R. Karjalainen, (1999),“Using Genetic Algorithms to Find Technical Trading Rules”, Journal of Financial Economics, Vol. 51, 245-271.
Altay-Salih, A., G. Muradoglu and M. Mercan, (2002),“Performance of the efficient frontier in an emerging market setting”, Applied Economics Letters, Vol. 9 Issue 3, 177-183.
Babalos, V., Kostakis, A. and Philippas, N., (2007),” Spurious results in testing mutual fund performance persistence: evidence from the Greek market.” Applied Financial Economics Letters, 2007, 3, 103–108
Ballestero, E. and C. Romero, (1996) , “Portfolio Selection: A Compromise Programming Solution”, Journal of the Operational Research Society, Vol. 47, No. 11, 1377-1386.
Ballestero, E., (2005) , “Mean-Semivariance Efficient Frontier: A Downside Risk Model for Portfolio Selection”, Applied Mathematical Finance, Vol. 12, No. 1, 1-15.
Berk, J., and R. Green, (2004) , ‘‘Mutual Fund Flows and Performance in Rational Markets.’’ Forthcoming, Journal of Political Economy
Bian, J. S., (1995) , “An Genetic-Algorithm Model for Taiwan Stock Index Portfolio” M.A. thesis, Graduate Institute of Information Management, National Chiao Tung University, in Chinese.
Blake, D. and Timmermann, A. (1998), “Mutual Fund Performance: Evidence from the UK”, European Finance Review, 2, 57-77.
Bollen, N. P.B. and Busse, J.A., (2004),“Short-Term Persistence in Mutual Fund Performance.” Review of Financial Studies 2005 18(2) , 569-597.
Brands, S. and D. R. Gallagher, (2005), “Portfolio selection, diversification and fund-of-funds: a note”, Accounting & Finance, Vol. 45 Issue 2, 185-197.
Breuer, W. and M. Gurtler, (2006) , “Performance Evaluation, Portfolio Selection, and HARA Utility”, European Journal of Finance, Vol. 12 Issue 8, 649-669.
Brown, S. J., and W. N. Goetzmann, (1995),“Performance Persistence”, Journal of Finance, Vol. 50, No. 2, 679-698.
Carhart, M. M., (1997) , “On persistence in mutual fund performance”, Journal of Finance, Vol. 52, No. 1, 57-82.
Carlson, R. S. (1970),”Aggregate performance of mutual funds”, Journal of Financial and Quantitative Analysis, 5, 1–31.
Casarin, R., Pelizzon, L. and Piva, A., (2008), Italian Equity Funds: Efficiency and Performance Persistence, ICFAI Journal of Financial Economics, 6 (1), 7-28.
Chan, K.S., (2008),” Applying Mean-Variance Model and Genetic Algorithms to Construct Optimal Weights of Portfolio of Funds.” M.A. thesis, Graduate Institute of Finance, National Cheng Kung University
Chang, C. C., (2003),“Construction of Stock Index Simulation Portfolio Using Genetic Algorithms” M.A. thesis, Graduate Institute of Accounting, National Taipei University, in Chinese.
Chang, T. J., N. Meade, J. E. Beasley and Y. M. Sharaiha, (1998) , “Heuristics for cardinality constrained portfolio optimisation” The Management School, Imperial College, London SW7 2AZ, UK.
Chang, T.J., Yang, S. C. and Chang, K.J., (2009),“Portfolio Optimization Problems in Different Risk Measures Using Genetic Algorithms.” Expert Systems with Applications 36,10529–10537
Chen, A. H. Y., F. C. Jen and S. Zionts, (1971),“The optimal portfolio revision policy”, Journal of Business, 44, 51-61.
Chen, L.H. and Huang, L.,(2008),“Portfolio Optimization of Equity Mutual Funds with Fuzzy Return Rates and Risks.” Expert Systems with Applications 36 , 3720–3727
Chiu, C. R., (1998) , “An Application of Genetic Algorithms on Portfolio Strategies” M.A. thesis, Graduate Institute of Economics, National Sun Yat-sen University, in Chinese.
Crama, Y. and M. Schyns, (2003),“Simulated annealing for complex portfolio selection problems”, European Journal of Operational Research 150, 546-571.
Deng, X. T., Z. F. Li and S. Y. Wang, (2005),“A minimax portfolio selection strategy with equilibrium”, European Journal of Operational Research, Vol. 166 Issue 1, 278-292.
Drakos, K. and Zachouris, P., (2007) ,”On performance persistence in the Greek equity fund market.” Global Business and Economics Review, 2007, vol. 9, issue 1, 75-91
Elton, E. J., M. J. Gruber and C. R. Blake, (1996),“The Persistence of Risk-Adjusted Mutual Fund Performance”, The Journal of Business, Vol. 69, No. 2, 133-157.
Goetzmann, W.N. and Ibbotson, R.G. (1994), “Do Winners Repeat? Patterns in
Mutual Fund Performance”, Journal of Portfolio Management, 20, 9-18.
Grinblatt, M. and Titman, S. (1992),“ The Persistence of Mutual Funds”, Journal of Finance, 47, 1977-1984.
Hendricks, D., Patel, J. and Zeckhauser, R. (1993), “Hot Hands in Mutual Funds: Short-Run Persistence of Relative Performance, 1974-1988”, Journal of Finance, 48(1), 93-130.
Holland, J., (1975) , “Adaptation in Natural and Artificial System”, MIT Press Cambridge, MA, USA.
Huang, X., (2006) , “Fuzzy chance-constrained portfolio selection”, Applied Mathematics & Computation, Vol. 177 Issue 2, 500-507.
Jensen, M. (1968),”The performance of mutual funds in the period 1945–
1964”, Journal of Finance, 23, 389–416.
Jensen, M. C., (1969) , “The performance of mutual funds in the period 1945-1964”, Journal of Finance, Vol. 23, No. 2, 389-416.
Konno, H., (1990) , “Piecewise linear risk function and portfolio optimization”, Journal of the Operational Research Society of Japan Vol. 33, No. 2, 139-156.
Konno, H., & Yamazaki, H. (1991),”Mean-absolute deviation portfolio optimization
model and its application to the Tokyo Stock Market”, Management Science, 37,
519–531
Konno, H., Waki, H., & Yuuki, A. (2002),”Portfolio optimization under lower partial
risk measures”, Asia-Pacific Financial Markets, 9, 127–140.
Korczak, J. J, 2001, “Portfolio Design and Simulation Using Evolution Based Strategy”, M.A. thesis, Graduate Institute of Finance & Banking, National Cheng Kung University
Lai, S. and Li, H., (2008), “The performance evaluation for fund of funds by comparing asset allocation of mean–variance model or Genetic Algorithms to that of fund managers”, Applied Financial Economics, 2008, 18, 483–499
Lai, J.H., (2007),” Using Mean-Variance Model and Genetic Algorithm to Find the Optimized Weights of Portfolio of Funds”, M.A. thesis, Graduate Institute of Finance, National Cheng Kung University
Lin, C.C. and Liu, Y.T.,(2006), “Genetic Algorithms for Portfolio Selection Problems with Minimum Transaction Lots.” European Journal of Operational Research 185, 393–404
Lin, C.,Hsu, S. and Chen, S.,(2008),” Applying Genetic Algorithms to Explore Fund of Funds on Efficient Frontier and Product Design.” The 3rd Intetnational Conference on Innovative Computing Information and Control (ICICIC'08)
Lintner, J., (1965) , “The valuation of risk assets and the selection of risky investments in stock portfolios and capital budgets”, Journal of Finance, Dec65, Vol. 20 Issue 4, 587-615.
Malkiel, B. (1995), “Returns from Investing in Equity Mutual Funds 1971-1991”, Journal of Finance, 50, 549-573.
Markowitz, H., (1952) , “Portfolio selection”, Journal of Finance, Vol. 7, Issue 1, 77-91.
Markowitz, H., P. Todd, G. Xu and Y. Yamane, (1993) , “Computation of mean-semivariance efficient sets by the Critical Line Algorithm”, Annals of Operations Research 45, 307-317.
Oh, K. J., T. Y. Kim and S. Min, (2005) , “Using Genetic Algorithms to support portfolio optimization for index fund management”, Expert Systems with Applications, Vol. 28 Issue 2, 371-379.
Oh, K. J., T. Y. Kim, S. H. Min and H. Y. Lee, (2006), “Portfolio algorithm based on portfolio beta using Genetic Algorithms”, Expert Systems with Applications, Vol. 30 Issue 3, 527-534.
Pogue, G. A., (1970) , “An Extension of the Markowitz Portfolio Selection Model to Include Variable Transactions’ Costs, Short Sales, Leverage Policies and Taxes”, Journal of Finance, Vol. 25, No. 5, 1005-1027.
Sharpe, W. (1966), ” Mutual fund performance”, Journal of Business, 39,119–138.
Sharpe, W. F., (1964) , “Capital Asset Prices: A Theory of Market Equilibrium under Conditions of Risk”, Journal of Finance Vol. 19, No. 3, 425-442.
Sharpe, W. F., (2007) , “Expected Utility Asset Allocation”, Financial Analysts Journal, Vol. 63 Issue 5, 18-30.
Shapcott, J., (1992), “Index Tracking: Genetic Algorithms for Investment Portfolio Selection”, Edinburgh Parallel Computing Centre, EPCC–SS92–24.
Soleimani, H., Golmakani, H. R. and Salimi, H., (2008),”Markowitz-Based Portfolio Selection with Minimum Transaction Lots, Cardinality Constraints and Regarding Sector Capitalization Using Genetic Algorithms” Expert Systems with Applications 36, 5058–5063
Treynor, J. L., (1965),“How to rate management of investment funds”, Harvard Business Review 43, 63-75.
Venugopal, M., S. Subramanian and U. S. Rao, (2004), “Usefulness of Genetic Algorithms Model for Dynamic Portfolio Selection”, Journal of Financial Management & Analysis, Vol. 17, Issue 1, 45-53.
Williamson, P. J. (1972),”Measurement and forecasting of mutual fund performance: choosing an investment strategy”, Financial Analysts Journal, 28, 78–84.
Xia, Y., Wang, S. and Deng, X.,(2000),” A Compromise Solution to Mutual Funds Portfolio Selection with Transaction Costs.” European Fournal of Operational Research 134,564-581
Yang, X.,(2006), “ Improving Portfolio Efficiency: A Genetic Algorithms Approach.” Computational Economics 28, 1–14
Yan, W., R. Miao and S. Li, (2007), “Multi-period semi-variance portfolio selection: Model and numerical solution”, Applied Mathematics and Computation, Vol. 194, 128-134.