Table 4.

Performance of ML model II and ML model III with different classification algorithms for training and test datasets

Algorithms	Precision	Recall	F1-score	AUC-ROC	Accuracy
Performance of ML model II with different classification algorithms on the test dataset
SVM	84.21	91.42	87.67	94.44	87.32
Random Forest	82.08	78.57	80.28	91.31	80.98
Extra Trees	82.21	80.18	81.14	91.85	81.67
AdaBoost	81.84	77.35	79.51	80.34	80.38
XGBoost	82.85	82.85	82.85	83.09	83.09
LR	85.29	82.85	84.05	92.06	84.50
Performance of ML model III with different classification algorithms on the test dataset
SVM	86.11	88.57	87.32	93.57	87.32
Random Forest	84.37	82.01	83.16	91.37	83.62
Extra Trees	83.29	84.09	83.67	91.21	83.83
AdaBoost	80.14	80.13	79.77	79.90	79.90
XGBoost	72.50	82.85	77.33	76.15	76.05
LR	88.57	88.57	88.57	92.06	88.73