本研究以ETF台灣50指數基金為研究標的，運用統計方法，模糊學習規則以及倒傳遞類神經網路等方法，利用不同之變數組合，建構4種預測模式組合，探討研究變數組合以及所使用方法之模式優劣。本研究整合預測模式，將依據文獻所選取之變數，主要有三大法人買賣超、券資比，以及具有連動性之國際股市指數，日經225指數、香港恆生指數、NASDAQ科技類股、道瓊工業指數、S&P500為輸入變數，對ETF台灣50 指數隔周收盤價作預測。
研究範圍為2009年5月27日至2013年12月27日。利用動態學習法，分為五個時期。實證結果顯示，預測誤差方面，以使用逐步迴歸篩選之變數執行之時間序列預測最好，投資報酬率方面，以統計方法所得到的投資報酬率優於買入持有。

SUMMARY
In this study, Taiwan 50 Index Fund ETF research subject, the use of statistical methods, fuzzy learning rules, and back-propagation neural network and other methods, to establish different combinations of variables to construct four kinds of combination forecasting model to explore the research variables and methods used in combination the mode pros and cons. This study integrates predictive model will be based on the variables selected literature, there are three major legal dealings over, voucher funding ratio, and has even mobility of international stock market index, the Nikkei 225 index, Hong Kong's Hang Seng Index, NASDAQ technology stocks, Road Joan industrial Average, S & P500 for the input variables of the Taiwan 50 Index ETF fortnightly closing price for the forecast.
The empirical interval is May 27, 20009 to December 27, 2013. Dynamic learning method is divided into five periods. The empirical results show that the prediction error terms, using stepwise regression variables to predict the best time to perform the sequence, return on investment, the ROI obtained by statistical methods is better than buy and hold.

中文部分:
1. 王文俊 (2005)，認識Fuzzy，第三版，台北，全華圖書公司。
2. 李惠妍 (2003)，「類神經網路與迴歸模式在台股指數期貨預測之研究」，成功大學企業管理學系專班，碩士論文。
3. 吳宗正 (2006)，投資技術分析，第六版，台北，華泰文化事業股份有限公司。
4. 陳順宇 (2003)，多變量分析，三版，華泰書局。
5. 謝劍平 (2006)，現代投資學:分析與管理，第三版，智勝文化。
6. 戴淑瑩 (2007)，「臺灣50指數ETF整合型預測之研究」，國立成功大學統計研究所，碩士論文。
7. 羅華強 (2011)，類神經網路─MATLAB的應用，第三版，高立圖書有限公司。

英文部分:
1. Armano, G., Marchesi, M., & Murru, A. (2005). A hybrid genetic-neural architecture for stock indexes forecasting. Information Sciences, 170(1), 3-33.
2. Box, G.E.P. & Jenkins, G.M. (1970). Time Series Analysis: Forecasting and Control. San Francisco: Holden Day.
3. Cattell, R. B. (1966). The scree test for the number of factors. Multivariate behavioral research, 1(2), 245-276.
4. Eun, C. S., & Shim, S. (1989). International transmission of stock market movements. Journal of financial and quantitative Analysis, 24(02), 241-256.
5. Fama, E. F. (1970). Efficient capital markets: A review of theory and empirical work*. The journal of Finance, 25(2), 383-417.
6. Jaffe, J., & Westerfield, R. (1985). The Week‐End Effect in Common Stock Returns: The International Evidence. The journal of finance, 40(2), 433-454.
7. Kanas, A., & Yannopoulos, A. (2001). Comparing linear and nonlinear forecasts for stock returns. International Review of Economics & Finance, 10(4), 383-398.
8. Kearney, C. (2001). The determination and international transmission of stock market volatility. Global Finance Journal, 11(1), 31-52.
9. Phylaktis, K., & Ravazzolo, F. (2005). Stock prices and exchange rate dynamics. Journal of International Money and Finance, 24(7), 1031-1053.
10. Tsay, R. S., & Tiao, G. C. (1984). Consistent estimates of autoregressive parameters and extended sample autocorrelation function for stationary and nonstationary ARMA models. Journal of the American Statistical Association,79(385), 84-96.
11. Wang, L. X. (2003). The WM method completed: a flexible fuzzy system approach to data mining. Fuzzy Systems, IEEE Transactions on, 11(6), 768-782.