Volatility Forecasting Using a Hybrid GJR-GARCH Neural Network Model

AbstractVolatility forecasting in the financial markets, along with the development of financial models, is important in the areas of risk management and asset pricing, among others. Previous testing has shown that asymmetric GARCH models outperform other GARCH family models with regard to volatility prediction. Utilizing this information, three popular Neural Network models (Feed-Forward with Back Propagation, Generalized Regression, and Radial Basis Function) are implemented to help improve the performance of the GJR(1,1) method for estimating volatility over the next forty-four trading days. During training and testing, four different economic cycles have been considered between 1997-2011 to represent real and contemporary periods of market calm and crisis. In addition to stress testing for different neural network architectures to assess their performance under various turmoil and normal situations in the U.S. market, their synergy along with another econometric model is also accessed