Abstract
Due to the tremendous growth in e-learning in recent years, there is a need to address the issue of attrition in online courses. Predictive modeling can help identify students who may be “at-risk” to drop out from an online course. This study examines various categorical classification algorithms and evaluates the accuracy of logistic regression (LR), neural networks (Multilayer Perceptron), and support vector machines (SVM) models to predict dropout in online courses. The analyses with LR, MLP, and SVM indicated that current college GPA is the strongest predictor of online course completion.
Recommended Citation
Bukralia, Rajeev, "Predicting Dropout in Online Courses: Comparison of Classification Techniques" (2010). MWAIS 2010 Proceedings. 19.
https://aisel.aisnet.org/mwais2010/19