Open access
Oct 2026
Comparing machine learning models for academic success prediction in online learning
Early-warning models must balance the detection of unsuccessful outcomes with the workload of student support. We compare logistic regression, a decision tree, a random forest, and gradient boosting using 32,593 records from the Open University Learning Analytics dataset. Sixteen features are evaluated at 30, 60, and 9...
S. V. Velychko, O. Chepurna, Олена Георгіївна Федоренко
· CTE Workshop Proceedings · 0 citations