Investigating the Role of Demographics in Predicting High Achieving Students

Researchers have observed the relationship between academic achievements and students’ demographical characteristics in physical classroom-based learning. In the context of online learning, recent studies were conducted to explore the leading factors of successful online courses. These studies investigated the impact of demographical features on students’ achievement in the online learning environment. Most works were presented via descriptive statistics or utilized big data with advanced classification algorithms. In this paper, we study the role of students’ demographics in predicting high achieving students in online courses. Obtained results show that the interaction of students with the virtual learning environment is more informative than the student’s demographical characteristics, which allows for the removal of demographical information without affecting the prediction models’ performance. In addition, the testing results present that cross-courses-trained predictive models are as effective as individual-courses-trained models.