Forecasting Exchange Rate Value at Risk using Deep Belief Network Ensemble based Approach

In this paper, we propose a new Value at Risk estimate based on the Deep Belief Network ensemble model with Empirical Mode Decomposition (EMD) technique. It attempts to capture the multi-scale data features with the EMD-DBN ensemble model and predict the risk movement more accurately. Individual data components are extracted using EMD model while individual forecasts can be calculated at different scales using ARMA-GARCH model. The DBN model is introduced to search for the optimal nonlinear ensemble weights to combine the individual forecasts at different scales into the ensembled exchange rate VaR forecasts. Empirical studies using major exchange rates confirm that the proposed model demonstrates the superior performance compared to the benchmark models.