Predicting Students Performance in Online Courses using Classification Techniques

Data Mining techniques have become widely used for several types of tasks, such as data classification. Data classification aims to classify data into set of classes based on trained model called classifier. Such techniques are used to extract important information needed to make decisions in different scopes, one of them is Education. This paper, applies several classification techniques on an academic dataset for online courses, to find the best classifier to predict the student performance, using certain features that might affect this performance. Classifiers used are Decision Tree, Artificial Neural Network, Support Vector Machine, and K-Nearest Neighbors. Experiments used real data and evaluated the models based on four performance measures: accuracy, precision, recall, and F-measure. Results show that Decision Tree and Artificial Neural Network achieved best results among other classifiers.