A Hybrid Approach Integrating Multiple ICEEMDANs, WOA, and RVFL Networks for Economic and Financial Time Series Forecasting

Table 3

The mean absolute percent error (MAPE) values of different prediction models.

Dataset	Horizon	MICEEMDAN -WOA-RVFL	RW	LSSVR	BPNN	ICEEMDAN -RW	ICEEMDAN -LSSVR	ICEEMDAN -BPNN
WTI	1	0.0036	0.0176	0.0177	0.0182	0.0200	0.0044	0.0055
	3	0.0080	0.0307	0.0309	0.0320	0.0331	0.0092	0.0094
	6	0.0113	0.0441	0.0449	0.0457	0.0458	0.1202	0.0130
USD/EUR	1	0.0006	0.0034	0.0034	0.0034	0.0044	0.0010	0.0010
	3	0.0015	0.0063	0.0063	0.0063	0.0071	0.0020	0.0021
	6	0.0022	0.0087	0.0088	0.0087	0.0094	0.0032	0.0031
IP	1	0.0012	0.0049	0.0057	0.0056	0.0053	0.0024	0.0022
	3	0.0023	0.0102	0.0140	0.0123	0.0104	0.0033	0.0033
	6	0.0032	0.0183	0.0279	0.0235	0.0184	0.0043	0.0049
SSEC	1	0.0020	0.0096	0.0096	0.0097	0.0111	0.0026	0.0026
	3	0.0044	0.0178	0.0178	0.0179	0.0185	0.0047	0.0051
	6	0.0065	0.0259	0.0259	0.0269	0.0268	0.0072	0.0074