自Markowitz於1952年提出平均數-變異數投資組合模型架構以來，如何在MV模型之效率前緣下，建立最佳投資組合，一直是各界研究及探討的議題。效率前緣上之投資組合通常都有高報酬伴隨著高風險或低報酬伴隨低風險的特性，使得投資者必須在期望報酬率與風險之間取捨而造成投資決策進退兩難，其計算過程複雜，當標的物數量很多的時候，亦可能造成無法即時求出最佳解的情形。
本研究以台灣上市電子股為研究對象，研究期間為2004/01/02~2007/5/25，使用人工智慧之方法提出新模型，以合理及簡便的方法解決問題。除此之外，有鑒於模型之特性以及投入資金水準之不同，本研究並與過去提出之模型比較，分析模型在過度反應及不同資金水準下的表現，使得在越接近現實之情形下，反應出模型之特性與優劣，做為投資者建立投資組合之參考。
實驗結果顯示，多數投資組合模型存在過度反應，且各種不同模型在不同資金水準下，表現並不相同。本研究所提出之動量權重灰預測傅立葉殘差修正模型，可以有效降低過度反應，並在考慮不同資金水準下，得到較高且較穩定的績效。此外，本研究提出動態投資線，其表示在不同資金水準下，投資人可選擇之最佳投資組合模型，以做為投資決策之參考指標。

Since Markowitz proposed the mean-variance portfolio model in 1952, how to set up the portfolio optimization, based on an efficient frontier of MV model, has continuously been discussed. Normally, the portfolios on the efficient frontier show a positive correlation between risk and return. Higher returns are always accompanied with higher risks, and vise versa. It leads to a dilemma for investors to make their decisions. Moreover, when too many securities or asset classes are put in the pool, it’s difficult to obtain a precise solution under some limit of time.
This research proposes a new model by applying the artificial intelligence in an attempt to find a rational and convenient solution to the portfolio optimization. The sample using in the research is Taiwan stock market during January 2004 to May 2007. In addition, the research compares with a few prior models and analyzes the performances in the different levels of over-reaction and different amount of capital invested. The results reflect the characteristics and the pros and cons of the models in more realized circumstances, and provide a good reference for portfolio building.
The results of this research show that the over-reaction appears in most portfolios models, and the performance of each model is quite dissimilar between different capital levels. Momentum Weight and Grey Fourier Model proposed from this research can reduce over-reaction effectively and has a higher and more stable performance between different capital levels. Furthermore, we provide a dynamic investment line to express the optimization-portfolio model in different capital levels to help making investment decisions.

中文部份
[1] 何怡慧 (1999)，「上市公司財務績效指標灰色預測模式之研究」，長榮管理學院經營管理研究所碩士論文。
[2] 林美珍 (1992)，「股票價格過度反應之方向、幅度與密度」，台灣大學財務金融研究所碩士論文。
[3] 翁德耀 (1998)，「以VAT風險計量模型衡量我國銀行外幣持有部位之市場風險」，國立台灣大學商學研究所碩士論文。
[4] 陳光華 (2000)，「台灣股市動能生命週期之再探討」，銘傳大學財務金融研究所碩士論文。
[5] 陳志玗 (2002)，「國內共同基金風險值之評估與夏普指數之運用」，東吳大學企業管理研究所碩士論文。
[6] 劉起朝 (2006)，「投資組合風險研究-以臺灣證券交易所臺灣50指數成分股為例」，東華大學企業管理學系碩士論文。
[7] 蔣柏廷、陳俊益、張剛誠 (2006)，「以灰預測修正模型預測北美半導體B/B值」，第十一屆灰色系統理論與應用研討會。
[8] 蔡劼麟 (1999)，「台灣股票市場價格動量與週轉率之循環研究」，銘傳大學財務金融研究所碩士論文。
[9] 鄭錦亞、遲國泰 (2001)，「基於差異係數σ / μ 的最優投資組合方法」，中國管理科學，9(1)，第1-5頁。
[10] 鄧聚龍 (1986)，「灰色預測與決策」，華中理工大學出版社。

英文部分
[1] Alexander, C.O. and Leigh, C.T. (1997), “On the covariance matrices used in value at risk models,” Journal of Derivatives 4 (Spring), pp. 50-62.
[2] Amihud, Y. and Mendelson, H. (1986),” Asset pricing and the bid-ask spread, “Journal of Financial Economics 17 (2), pp. 223-249.
[3] Campbell, J.Y., Grossman, S.J. and Wang, J. (1993), “Trading volume and serial correlation in stock returns,” Quarterly Journal of Economics 107, 905-939.
[4] Campbell, R., Huisman, R. and Koedijk, K. (2001), “Optimal portfolio selection in a value-at-risk framework,“ Journal of Banking and Finance 25 (9), pp. 1789-1804.
[5] Chopra, V.K., Hensel, C.R. and Turner, A.L. (1993), “Massaging mean-variance inputs: returns from alternative global investment strategies in the 1980s,” Management Science 39 (7), pp. 845-855.
[6] Conrad, J., Hameed, A. and Niden, C. (1994), “Volume and autocovariances in short-horizon individual security returns, “Journal of Finance 49 (4), pp. 1305-1329.
[7] Datar Vinay, T., Naik, N.Y. and Radcliffe, R. (1998), “Liquidity and stock returns: An alternative test,” Journal of Financial Markets 2 (August), pp. 203-219.
[8] DeBondt, W. and Thaler, R. (1985), “Does the stock market overreact,” Journal of Finance 40, pp. 557-581
[9] Jegadeesh, N. and Titman, S. (1993), “Returns to buying winners and welling losers: implications for stock market efficiency,” Journal of Finance 48 (1), pp. 65-91
[10] Kallberg, J.G. and Ziemba, W.T. (1984), “Mis-specification in portfolio selection problems,” Risk and Capital, pp. 74-87.
[11] Dowd, K. (1999), “A value at risk approach to risk-return analysis, ” The Journal of Portfolio Management, pp. 60-67.
[12] Konno, H. and Yamazaki, H.(1991),“Mean-absolute deviation portfolio optimization model and its applications to Tokyo stock market,” Management Science 37 (5), pp. 519-531
[13] Lee, C. and Swaminathan, B. (2000), “Price momentum and trading volume,” Journal of Finance 55, pp.2017-2069
[14] Lehmann, B.N. (1990), “Fads, martingales, and market efficiency, “ Quarterly Journal of Economics 105 (1), pp. 1-28.
[15] Markowitz, H.M. (1952), “Portfolio selection, “ Journal of Finance 7 (1), pp. 77-91
[16] Murthi, B.P.S. and Choi, Y.K., Desai, P. (1997), “ Efficiency of mutual funds and portfolio performance measurement: A non-parametric approach, ”European Journal of Operational Research 98 (2), pp. 408-418.
[17] Sharpe, W. F. (1966), “Mutual fund performance,” Journal of Business 39 (1), pp. 119-138.
[18] Sharpe, W.F. (1994), “The Sharpe ratio,” Journal of Portfolio Management 21 (1), pp. 49-58.