Forecasting Computer Products Sales by Integrating Ensemble Empirical Mode Decomposition and Extreme Learning Machine

Table 4

The forecasting results of NB and DC using the single ELM, single SVR, single BPN, EMD-ELM, and the proposed EEMD-ELM models.

Computer products	Models	RMSE	MAPE	MAD	Training time (s)
	Single ELM	76.87	3.84%	31.21	0.0382
	Single SVR	77.02	3.91%	31.31	0.0903
NB	Single BPN	78.11	3.95%	32.05	0.1103
	EMD-ELM	62.09	5.37%	40.45	0.0713
	EEMD-ELM	56.33	3.53%	28.01	0.0801
	Single ELM	22.94	5.53%	16.31	0.0365
	Single SVR	23.02	5.59%	16.65	0.0872
DC	Single BPN	22.96	5.54%	16.31	0.0981
	EMD-ELM	22.38	4.53%	15.88	0.0695
	EEMD-ELM	11.99	4.39%	9.22	0.0797