Chinese Currency Exchange Rates Forecasting with EMD-Based Neural Network

Table 2

NMSE comparisons for different models.

	1-day	5-day	10-day	20-day	30-day
Panel A: MLP model
MLP(3)	0.0231	0.0874	0.2118	0.3698	0.5888
MLP(5)	0.0204	0.0854	0.2088	0.3939	0.5723
MLP(5,3)	0.0285	0.0943	0.2088	0.3623	0.4746
MLP(6,4)	0.0376	0.0896	0.2021	0.3613	0.5453
Panel B: EMD-MLP model
EMD(-1)-MLP(3)		0.0823	0.2120	0.3894
EMD(-1)-MLP(5,3)			0.2111	0.3836	0.5447
EMD(-2)-MLP(3)	0.0207			0.3760	0.5258
EMD(-2)-MLP(5,3)				0.3667	0.5258
EMD(-3)-MLP(3)	0.0434
EMD(-3)-MLP(5,3)	0.0419
Panel C: EMD-MLP model
EMD(0)-MLP(3)
EMD(0)-MLP(5,3)
EMD(-1)-MLP(3)
EMD(-1)-MLP(5,3)
EMD(-2)-MLP(3)
EMD(-2)-MLP(5,3)
Panel D: random walk model
No drift	0.0144	0.0861	0.2349	0.5323	0.9357
With drift	0.0148	0.0973	0.2834	0.6981	1.2954

Consider the CNY from January 2, 2006, to December 21, 2015, with a total of 2584 observations. This table compares the forecasting performance, in terms of the NMSE, for the MLP, EMD-MLP, and EMD-MLP models. We report the NMSE as percentage for l-day ahead predictions where and 30. The DM test [38] is used to compare the forecast accuracy of EMD-MLP (EMD-MLP) model and the corresponding MLP model. , , and denote statistical significance at 1%, 5%, and 10%, respectively. For each length of prediction, we mark the minimum NMSE as bold.