Effective Utilization of Data for Predicting COVID-19 Dynamics: An Exploration through Machine Learning Models

Table 16

RAE values of support vector regression models for fatal cases.

Forecast period (days)	Cumulative cases				Daily cases
	Germany	Japan	South Korea	Ukraine	Germany	Japan	South Korea	Ukraine
Train 3	0.02106	0.01548	0.009339	0.037708	0.525147	0.362153	0.530935	0.264905
Test 3	1.175869	2.261846	1.357158	0.624051	0.88613	1.255252	1.652311	0.5763
Train 7	0.03594	0.029272	0.02777	0.06515	0.533342	0.395006	0.566022	0.29647
Test 7	1.534016	1.651911	0.341557	0.15409	0.825802	0.419491	0.396898	0.547401
Train 14	0.063465	0.054886	0.083077	0.108502	0.632977	0.486001	0.620467	0.385795
Test 14	1.707127	1.591522	0.150748	0.257448	0.802261	0.602924	0.667564	0.688777
Train 21	0.090928	0.081189	0.134317	0.16315	0.714705	0.603202	0.724743	0.444301
Test 21	1.65779	1.575147	0.078365	0.431956	0.776902	0.538983	0.751257	0.847105
Train 30	0.1304	0.126756	0.208699	0.232772	0.817074	0.696338	0.772135	0.590408
Test 30	1.732633	1.589979	0.043109	0.626331	0.744521	0.552149	0.806762	0.919628