以類神經網路建構風險值模型

Constructing a VaR model by Artificial Neural Network

許力夫(Hsu Li-Fu)

指導教授 ： 林士貴 ； 張宜武

國立政治大學/理學院/應用數學系/碩士(2018年)

https://doi.org/10.6814/THE.NCCU.MATH.007.2018.B01

摘要

本研究利用2008/01/04至2018/09/28台灣加權指數進行分析與評估風險值之預測效果。研究成果與貢獻如下：一、延伸GARCH模型，假設即期波動度與非預期變動、歷史波動度呈非線性關係，透過類神經網路來捕捉更多非線性槓桿、波動叢集等效果。二、針對不同模型，分別利用最大概似法、反向傳播演算法等進行參數估計與訓練網路。實證結果顯示新模型對於波動度具有較好之配適能力。三、與變異數法、歷史模擬法、GARCH 模型比較，在95%信心水準下新模型所計算之風險值具有較低之穿透率。因此新模型所計算之風險值應可有效改善企業投資時所需提撥之準備金，主管機關亦可透過此模型來訂定投資人所需付出之保證金，皆可降低信用風險與穩定金融市場。本研究可提供上述產業評估風險時較為精準、客觀與較有效率之工具。

關鍵字

風險值 ； 類神經網路 ； GARCH模型 ； 反向傳播演算法 ； 共變異數法 ； 歷史模擬法

並列摘要

We analyze the VaR prediction by using the TWII data from 2008/01/04 to 2018/09/28. The contribution and results are as following: First, to extend the GARCH model, we assume spot volatility, unexpected volatility and historical volatility have non-linear relationship. By training neural network, we capture more non-linear lever effects and cluster volatility effects. Second, compared with different VaR models, we use Max Likelihood method to estimate the parameters and Backpropagation to train the neural network. The results show that the new model fits the volatility better than others. Third, compare the new model with other methods, VaR values predicted by new model have lower ABLF values. Therefore, the VaR values evaluated by new model can improve the reserve fund when the enterprise invests. The financial authority also can set the security deposit by using new model. This study can provide the abovementioned industrial a precise and objective tool to evaluate the risk.

並列關鍵字

Value-at-Risk(VaR) ； Neural Network ； Variance-covariance method ； Historical simulation method ； GARCH(1,1) model ； Backpropagation

參考文獻

英文文獻

[1] Chen C.T. (2009), “Forecasting Value at Risk (VAR) in the futures market using Hybrid method of Neural Networks and GARCH model”, 2009 International Joint Conference on Computational Sciences and Optimization p17-21.

[2] Moreno J.J.(2011),”Artificial neural networks applied to forecasting time series”, Psicothema 2011. Vol. 23 n^。2, p322-329.

[3] Chen X.L(2009), “A Statistical Neural Network Approach for Value-at-Risk.”, 2009 International Joint Conference on Computational Sciences and Optimization p17-21.

[4] Engle(1982), “Autoregressive Conditional Heteroscedasticity with Estimation of the Variance in U.K. Inflation,” Econometrica, Vol. 50, 1982, p987-1008..