Prediction of Students’ Performance in E-learning Courses

A significant amount of research works has tackled the problem of students’ performance prediction. The introduction of learning management systems enabled providing teachers and students with accurate predictions to take remedial actions, and enhance students’ achievement. This paper proposes a new students’ performance prediction model based on different academic and non-academic features. We use a filter-based feature selection model to select a subset of the features that can describe the input data and reduce feature space dimensionality. A subsequent classification algorithm classifies students’ feature vectors to predict student performance. The obtained results reveal a strong relationship between students’ behavioral features and academic achievement. Moreover, results indicated that a Random Forest classifier with 5-fold cross-validation outperforms other algorithms, including Support Vector Machine, K-nearest neighbor, and Artificial Neural Network. Applying a Random Forest classifier on the reduced number of features provide 83.33%, 82.8, and 83% for accuracy, precision, and recall, metrics, respectively.