Alternative Volatility Models for Risk Management and Trading: An application . . .

In this paper, we examine the forecasting ability of several alternative models of currency volatility applied to two foreign exchange rates: EUR/USD and USD/JPY which, according to the BIS (2004), represent 45 % of the $1.9 trillion daily trading volume on the world currency markets. Benchmarked against two naïve ‘random walk ’ models and a RiskMetrics volatility model, the predictive ability of the AR(p), GARCH(p,q), new modelling approaches such as Stochastic Variance (SV) and Neural Network Regression (NNR) models, and two different model combinations is assessed at the 1-, 5- and 21-day horizons not only in terms of traditional forecasting accuracy measures but also in terms of risk management efficiency under the Value-at-Risk (VaR) framework and trading performance with a volatility filter strategy