Value-at-risk forecasting with combined neural network model

Conference Paper · January 2010
DOI: 10.1109/ICNC.2010.5583173 · Source: DBLP
Conference: Sixth International Conference on Natural Computation, ICNC 2010, Yantai, Shandong, China, 10-12 August 2010


    This paper develops a neural network model for solving the Value-at-risk forecasting problems. The application of forecasting methods in neural network models is discussed, which involves normal-GARCH model and grey forecasting model. Compared to the use of traditional models, the new method is fast, easy to implement, numerically reliable. After describing the model, experimental results from Chinese equity market verify the effectiveness and applicability of the proposed work.