International Journal of Educational Technology in Higher Education

Table 8 Performance of ML models (AUC ROC) classifying students into Good and AtRisk groups

From: Framework for automatically suggesting remedial actions to help students at risk based on explainable ML and rule-based models

	XGB	LightGBM	SVM	GaussianNB	ExtraTrees	Bagging	RandomForest	MLP
CP	0.9447	0.9690	0.9220	0.9349	0.9918	0.9422	0.9601	0.9231
CP + RF	0.9842	0.9781	0.9390	0.9606	1.000	0.9777	0.9980	0.9455

\(-\)CP checkpoints; RF risk flag
\(-\)Checkpoints before MT from D3 dataset are used as model inputs

Back to article page