本研究首次提出以未來臨界報酬率為輸出變數，利用兩種類神經網路(Artificial Neural Network)估算國內電子股代表樣本報酬率的風險值(Value at Risk , VaR)。在研究設計上考慮到使用不同期長來計算自變項所帶來的影響而產生兩種預測方法。本研究並以回顧檢定(Backtesting )檢討藉由臨界值報酬率作為類神經估計法與一般以變異數/共變數法或蒙地卡羅模擬法所估算出VaR的差異。

綜合本研究，在學術及實務上的貢獻有下列四點：

1. 設計臨界報酬率作為估算VaR的方式，可以避免以往計算VaR時，報酬率分配主觀給定的問題。

2. 相關研究過去並未同時涉及類神經網路與VaR，而本研究首次應用類神經網路估算VaR。

3. 本文亦提出以多種不同的基本變數衡量期長來估算VaR，或可幫助界定差異的研究設計。

4. 本研究使用類神經網路可能的一項限制是報酬率臨界值 的設計方式；而類神經網路可能勝出其它預測工具的理由可能是 (1)學習到隱性因子的特性 (2)預測方式為非線性 (3)毋須依賴常態或特定分配之假設。以往類神經網路研究在賽馬決定各工具優劣時，較少探究類神經勝出或落敗的理由，而這卻是本研究設計的焦點。

一、中文部份：
1. 蔡瑞煌 (1995)，類神經網路概論，台北：三民書局。
2. 蔡瑞煌、邱奕德、劉曦敏，「應用理解神經網路系統於臺灣股價指數之分
析及預測」，經濟研究，三十四卷，二期，民國85年7月，頁171-200。
二、英文部份：
1. Ahn, Dong-Hyun; Boudoukh, Jacob; Richardson, Matthew and
Whitelaw, Robert F,” Optimal Risk Management Using
Options,” Journal of Finance, Feb,1999,pp. 359-375.
2. Alexander C.O. and C.T. Leigh. “On the Covariance Matrices
Used In Value at Risk Models,” The Journal of Jerivatives,
Spring, 1997, pp. 50-62.
3. Beder, T. S., “VAR: Seductive but Dangerous,” Financial
Analysts Journal, September/ October 1995, pp. 12-24.
4. Chiou, Y., Liu, S. and Tsaih, R., “Applying Reasoning
Neural Networks to the Analysis and Forecast of Taiwan's
Stock Index Variation,” Taipei Economics Inquiry , 1996,
pp.171-200.
5. David J. Ginzl., “How to Establish a Comprehensive Risk-
Management Program,” Commercial Lending Review, Summer
1997, pp. 31-35.
6. Duffie, D., and J. Pan “An Overview of Value at Risk,” The
Journal of Derivatives, Spring, 1997, pp. 7-49.
7. Hull, J., and A. White. “Value at Risk When Daily Changes
in Market Variables Are Not Normally Distributed,” The
Journal of Derivatives, Spring, 1998, pp. 9-19.
8. Jorion, P., “Risk: Measuring the Risk in Value at Risk,”
Financial Analysts Journal, November/December 1996, pp. 47-
56.
9. Jorion, P., (1997) Value at Risk: The New Benchmark for
Controlling Market Risk Professional Publication, U.S.A :
Iriwin
10. Paul H. Kupiec, “Techniques for Verifying the Accuracy of
Risk Measurement Models,” The Journal of Derivatives
Winter, winter 1995,pp. 73-85.
11. Tsaih, R., “Reasoning Network Networks,” In Ellacott, S.,
J. Mason and Anderson, I. (Eds.), Mathematics of Neural
Networks: Models, Algorithms and Applications, Kluwer
Academic Publishers, London, 1997,pp. 366-371.
12. Tsaih,R.,Chen, W. and Lin,Y. , “Application of Reasoning
Neural Networks for Financial Swaps,” Journal of
Computational Intelligence in Finance, May 1998, pp.27-37.
13. Tsaih,R.,Hsu,Y., and Lai,C., “Forecasting S&P500 Stock
Index Futures with the Hybrid AI System,” Decision Support
Systems, Jun 1998,pp.161-174.
14. Venkat, Shyam; Malhotra, Satyan. , “Establishing a Value-
at-Risk Framework,” Mortgage Banking, Aug 1998,pp. 83-86.
15. Venkataraman, “Value at Risk for Normal Distribution―the
Use of Quasi Bayesian Estimation Techniques,” Economic
Perspectives,1997,pp.12