Table 6.

The comparison between improved traditional algorithms and machine learning algorithms.

	Model	Accuracy	ROC_AUC	Precision	Recall	F1
Traditional Model	Logistic Regression	0.748	0.747	0.741	0.776	0.758
Traditional Machine Learning Model	Random Forest	0.818	0.818	0.816	0.829	0.822
	Decision Tree	0.726	0.725	0.714	0.77	0.74
	BernoulliNB	0.698	0.700	0.700	0.719	0.708
	KNeighbors	0.746	0.745	0.735	0.782	0.759
	GaussianNB	0.600	0.595	0.567	0.908	0.698
Ensemble Learning Models	XGBoost	0.819	0.819	0.822	0.821	0.822
	Catboost	0.815	0.814	0.806	0.836	0.821
	Lightgbm	0.802	0.802	0.801	0.812	0.806