Application of machine learning methods for predicting under-five mortality: analysis of Nigerian demographic health survey 2018 dataset

Table 3 Performance evaluation of the selected ML algorithms for U5M prediction

Training-Test ratio	Measures	NB	LR	SVM	k-NN	ANN	J48	RF
70/30	TP Rate	0.82	0.87	0.87	0.88	0.89	0.88	0.89
	FP Rate	0.18	0.13	0.13	0.12	0.11	0.12	0.11
	Precision	0.84	0.87	0.87	0.88	0.89	0.88	0.89
	F-Measure	0.82	0.87	0.87	0.88	0.89	0.88	0.89
	MCC	0.66	0.75	0.75	0.77	0.77	0.77	0.79
	Accuracy	82.18	87.32	87.3	88.26	88.71	88.35	89.25
	AUROC	0.92	0.95	0.87	0.94	0.96	0.93	0.96
80/20	TP Rate	0.82	0.87	0.87	0.88	0.89	0.89	0.90
	FP Rate	0.18	0.13	0.13	0.12	0.11	0.11	0.11
	Precision	0.84	0.87	0.88	0.88	0.89	0.89	0.9
	F-Measure	0.82	0.87	0.87	0.88	0.89	0.89	0.9
	MCC	0.66	0.75	0.75	0.77	0.78	0.77	0.79
	Accuracy	82.00	87.39	87.43	88.41	88.82	88.61	89.47
	AUROC	0.91	0.95	0.87	0.94	0.96	0.94	0.96
10-fold	Sensitivity	0.82	0.87	0.88	0.89	0.89	0.89	0.89
	FP Rate	0.18	0.13	0.13	0.12	0.11	0.11	0.11
	Precision	0.84	0.87	0.88	0.89	0.89	0.89	0.89
	F-Measure	0.82	0.87	0.88	0.89	0.89	0.89	0.89
	MCC	0.65	0.75	0.75	0.77	0.78	0.77	0.79
	Accuracy	81.95	87.29	87.47	88.49	89.02	88.58	89.4
	AUROC	0.91	0.95	0.88	0.94	0.96	0.94	0.96

ISSN: 1472-6947