Forecasting exchange rates using general regression neural networks (Q1579016)

In this study, we examine the forecastability of a specific neural network architecture called general regression neural network (GRNN) and compare its performance with a variety of forecasting techniques, including multi-layered feedforward network (MLFN), multivariate transfer function, and random walk models. The comparison with MLFN provides a measure of GRNN's performance relative to the more conventional type of neural networks while the comparison with transfer function models examines the difference in predictive strength between the non-parametric and parametric techniques. The difficult to beat random walk model is used for benchmark comparison. Our findings show that GRNN not only has a higher degree of forecasting accuracy but also performs statistically better than other evaluated models for different currencies.