Skip to main content
International Journal of Educational Technology in Higher Education

Table 4 Performance of classification models in predicting students’ groups from checkpoints before the midterm exam (datasets D1 and D2)

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

Dataset

D1

D2

Predictors

Qz1, HW1, Qz2,HW2

Qz1, HW1, Qz2

Correlation

Positive 0.66%

Positive 0.54%

Best ML classifier

ExtraTrees

ExtraTrees

Accuracy

0.86

0.87

ROC AUC

0.96

0.95

Back to article page