Table 4. Performance parameter values for five machine learning algorithms before and after over-sampling.

	Algorithms	Accuracy	Precision	Recall	F1 score	AUC
Before oversampling	DT	0.743	0.333	0.217	0.263	0.688
	RF	0.780	0.455	0.217	0.294	0.754
	LR	0.771	0.429	0.261	0.324	0.733
	SVM	0.798	0.667	0.087	0.154	0.712
	XGBoost	0.817	0.615	0.348	0.444	0.726
After oversampling	DT	0.744	0.828	0.616	0.707	0.813
	RF	0.797	0.823	0.756	0.788	0.857
	LR	0.640	0.640	0.640	0.640	0.739
	SVM	0.663	0.689	0.593	0.638	0.767
	XGBoost	0.814	0.846	0.767	0.805	0.881

Abbreviations: AUC, area under the curve; DT, decision tree; RF, random forest; LR, logistic regression; SVM, support vector machine; XGBoost, extreme gradient boosting.