在證券交易市場裡，大家最關心的莫過於預測股價趨勢了。類神經網路有大量相互連結的處理單元，可以透過內部網路系統的演算法來學習輸入與輸出之間的關係，從許多文獻均證明類神經能準確處理非線性問題，如股價預測。本研究擬結合經濟附加價值與財務指標來預測股價，是否對於股價有關聯性，以及於較多歷史資料量下是否有較大的預測準確性，希以採用類神經網路(ANN)能準確預測台灣光電產業股價。此研究資料從民國94 年第一季至民國96 年第一季，共九季資料，資料來源篩選自台灣經濟新報資料庫共90 間光電公司。本研究發現：所建構的類神經網路模型預測出光電產業股價具有準確性，相關係數高達0.98；加入每股EVA 變數，對類神經網路模型預測能力有提升作用；對於歷史資料量多寡類神經網路預測能力差別不大，探討其原因可能為股票市場對於長期財務因素反應不足，及景氣循環等因素。

The most concerned issue for participants in stock market is to predict the trend of stock price. Artificial neural networks (ANN), a computing system containing many nonlinear computing units or nodes interconnected by links, is a well-tested method for financial analysis in the stock market. This study aims to find whether 10 financial ratio and Economic Value Added (EVA) are beneficial to stock price forecasting by using neural networks under different terms of history horizon, especially in Optoelectronics industry. The research period consists of 9 seasons, from Jan. 2005 to Jan. 2007. The financial data of 90 Optoelectronics companies are extracted from the TEJ database. The empirical findings of this research are ：First, the research constructed an artificial neural network model with higher accuracy of prediction, and the correlation coefficient is 0.98. Second, adding the EVA variable can enhance the prediction accuracy of ANN approach. Third, it makes no difference to the prediction ability of ANN, whether the quantity of input data is big or small.

摘要 i
ABSTRACT ii
誌謝 iii
目錄 iv
表目錄 vi
圖目錄 vii
一、 緒論 1
1.1 研究背景與動機 1
1.2 研究目的與方法 1
1.3 研究限制 1
1.4 研究流程 2
二、 文獻探討 4
2.1 光電產業概況 4
2.2 經濟附加價值 8
2.2.1 企業評價 8
2.2.2 經濟附加價值簡介 8
2.2.3 經濟附加價值與傳統會計方法之比較 9
2.2.4 經濟附加價值的會計調整科目 9
2.2.5 經濟附加價值與市價相關性實證研究文獻探討 12
2.3 類神經網路 12
2.3.1 資料探勘 12
2.3.2 類神經網路簡介 13
2.3.3 類神經網路架構與類型 14
2.3.4 類神經網路與統計方法相比其優缺點 16
2.3.5 類神經網路於財務領域之運用 17
2.4 倒傳遞類神經網路 18
三、 研究方法 21
3.1 研究範圍與對象 21
3.2 經濟附加價值之計算 22
3.2.1 經濟附加價值理論架構 22
3.2.2 經濟附加價值的會計調整項目 23
3.2.3 加權平均資金成本 24
3.3 研究變數之選取 25
3.4 類神經網路架構 27
3.5 倒傳遞網路模型重要參數設定 27
3.6 倒傳遞網路應用之可能面臨之限制與網路評估 28
3.6.1 倒傳遞應用可能面臨之限制 28
3.6.2 網路評估 28
四、 實證結果與分析 30
4.1 網路測試步驟 30
4.2 倒傳遞類神經網路研究結果 31
4.2.1 各項網路架構和參數設定 31
4.2.2 探討每股EVA加入與否對股價預測能力之影響 32
4.2.3 探討歷史資料輸入值多寡對股價預測能力之影響 35
4.2.4 總結 35
五、 結論與建議 38
5.1 研究結論 38
5.2 研究建議 38
參考文獻 40
附錄 一 43
附錄 二 44
附錄 三 47
附錄 四 48
附錄 五 49
附錄 六 50

中文部分

王信陽等編寫，2008，2007-2008年全球光電市場及台灣光電產業總論,光電科技工業協進會PIDA

王婼葳，2006，股價與公司價值在評價-EVA的應用，國立中山大學財務管理研究所碩士論文

李武隆，2000，績效衡量指標與股票報酬關聯性之研究，國立台灣大學會計學研究所碩士論文

涂宏任，2000，經濟附加價值解釋科技產業經營績效能力之研究，國立中正大學企業管理研究所碩士論文

黃紋萍，2004，兩稅合一經濟附加價值與股價之關聯性實證研究，國立中山大學財務管理研究所碩士論文

葉怡成，2001，應用類神經網路，儒林圖書有限公司

蔡湘萍，2000，銀行績效指標的選擇－EVA與會計指標孰優，國立中正大學財務金融研究所碩士論文

蔡爵穗，2000，以附加經濟價值(EVA)評估中油之經營績效，國立台灣大學會計學研究所碩士倫文


英文部分

Abarbanell, J. S. and Bushee, B. J., 1997. Fundamental Analysis, Future Earnings, and Stock Prices. Journal of Accounting Research, 35(1): 1-24.
Edward, A., 1968. Financial Ratios, Discriminant Analysis and the Prediction of Corporate Bankruptcy, Journal of Finance, 23(4): 589-609.
Biddle, G.C., Bowen, R.M. and Wallance, J.S., 1999. Evidence on EVA, Journal of Applied Corporate Finance, 12( 2): 69-72.

Biddle, G..C., Bowen, R.M. and Wallance, J.S., 1997. Does EVA Beat Earnings? Evidence on Associations with Stock Returns and Firm Values, Journal of Accounting and Economics, 24: 301-336.

Chen, S. and Dodd, J., 2001.Operating Income, Residual Income and EVA: Which Metric Is More Value Relevant. Journal of Managerial Issues , 13(1): 65-86.

Chou, S.C., Yang, C.C., Chan, C.H. and Lai, F., 1996. A Rule-based Neural Stock Trading Decision Support System. Proceedings of the IEEE/IAFE International Conference on Computational Intelligence for Financial Engineering, 24-26.

Chuck, K., Rizzuto, R., and Case, J., 2000. Managing by the Numbers: A Commonsense Guide to Understanding and Using Your Company’s Financials, Cambridge: Mass Inc.

Donaldson, R.G. and Kamstra, M., 1996. A New Dividend Forecasting Procedure That Rejects Bubbles in Asset Prices: The Case of 1929’s Stock Crash, Review of Financial Studies 9(2): 333-383.

Drucker, P.F., and Eccles, R.G.,1991-1998. Harvard Business Review on Measuring Corporate Performance, New York: Harvard Business Review School.

Ehrbar, A., 1998. EVA：The Real Key to Creating Wealth, New York: John Wiley& Sons Inc.

Frawley, W. J., Piatetsky-Shapiro, G.. and Matheus, C. J.,1991. Knowledge Discovery in Databases: An Overview. Cambridge: AAAI/MIT Press.

Gencay, R., 1996. Nonlinear Prediction of Security Returns with Moving Average Rules, Journal of Forecasting, 15(3): 165-174.

Hamilton, R.,1777. An Introduction to Merchandize, Edinburgh: J. Balfour.

Stern, J. M., 1993.Value and People Management,Corporate Finance, 104: 35-37.

Lee, J., Cho, S.and Baek, J., 2003. Trend Detection Using Auto-Associative Neural Networks : Intraday KOSPI 200 Futures,. Proceedings of IEEE International Conference on Computational Intelligence for Financial Engineering, 417-420.

Lehn, K. and Makhija, A. K., 1996. EVA and MVA as Performance Measures and Signals for Strategic Change, Strategy & Leadership, 24: 34-38.

Marshall, A.,1890. Principle of Economics, London: Macmillan Press.

McCulloh, W.S. and Pitts, W., 1943. A Logical Calculus of the Ideas Immanent in Nervous Activity, Bull. Math. Biophys, 5: 115–133.

Lam, M., 2004, Neural Network Techniques for Financial Performance Predication: Integration Fundamental and Technical Analysis, Decision Support Systems,37: 567-581

O’Byrne, F., 1996. EVA and Market Value, Journal of Applied Corporate Finance, 9(1): 116-125.

Ou, J.A. and Penman, S.H., 1989. Financial Statement Analysis and the Prediction of Stock Returns, Journal of Accounting and Economics, 11(1): 295-329

Parker, D.B., 1985. Learning Logic: Casting the Cortex of the Human Brain in Silicon, TR-47,Center for Computational Research in Economics and Management Science, MIT, Cambridge, MA.

Rumelhart, D.E., Hinton, G.E. and Williams, R.J., 1986. Learning Representations by Back-Propagating Errors, Nature 323: 533-536.

Solomons, D., 1965.Divisional Performance: Measurement and Control, New York: Financial Executives Research Foundation Inc.

Walczak, S.,2001. An Empirical Analysis of Data Requirements for Financial Forecasting with Neural Networks, Journal of Management Information Systems, 17(4): 203-222.

Tully, S., 1993. The Real Key to Creating Wealth. Fortune, New York, 128(6): 38-50.

Turban, E., 1995.Decision Support Systems and Expert Systems, New Jersey: Prentice Hall, Inc.

Wasserman, P. D., 1989. Neural Computing: Theory and Practice, New York: Van Nostrand Teinhold.

Werbos, P. J., 1974. Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences. Ph.D thesis, Harvard University.

Wood, D. and Dasgupta, B., 1994. Modeling and Index of the French Capital Market, Economic and Financial Computing, Autumn/ Winter: 119-136.

Wood, D. and Dasgupta, B.,1996. Classifying Trend Movements In the MSCI U.S.A. Capital Market Index - A Comparison of Regression, Arima and Neural Network Methods. Computers and Operations Research, 23(6): 611-622.

Young, S.D. and O’Byrne, S.F., 2000. EVA and Value Based Management : A Practical Guide to Implementation, New York: McGraw Hil

Zhu, X., Wang, H., Xu, L., and Li, H., 2008. Predicting Stock Index Increments by Neural Networks：The Role of Trading Volume under different horizons, Expert Systems with Applications, 34:3043-54


網站部分

拓墣產業研究所，http://www.topology.com.tw