Table 5.

Performance of GBM in the prediction of recovered and active cases in Delhi, India

Performance parameter	Distribution
	Gamma	Quintile	Poisson	Laplace	Huber	Tweedie	Gaussian
Recovered cases
MSE	9500.73	25,376.32	533.36	23,019.17	16,594.05	1129.63	2476.93
RMSE	97.47	159.30	23.09	151.72	128.82	33.61	49.77
MAE	48.19	66.21	13.45	58.38	49.86	18.69	32.87
MRD	9.14	33.11	−821.58	58.38	3717.56	1.39	2476.93
R2	0.70	0.21	0.98	0.28	0.48	0.96	0.92
Active cases
MSE	132,171.40	124,920.40	55,572.56	139,083.10	58,240.21	57,000.78	73,851.49
RMSE	363.55	353.44	235.74	372.94	241.33	238.75	271.76
MAE	243.64	230.35	117.85	201.10	151.60	139.85	160.40
MRD	15.39	115.18	−10,037.81	201.10	31,323.97	2.65	73,851.49
R2	0.62	0.64	0.84	0.60	0.83	0.84	0.79

Note: R2 (coefficient of determination), MSE (mean square error), RMSE (root mean square error), MAE (mean average error), and MRD (mean residual deviance)