Prediction MOOC’s for student by using machine learning methods

Abstract

MOOCs are a new wave of remote learning that has revolutionized it since its inception, allowing teachers to teach a large group of students at the same time, in the same course, across all disciplines, without even gathering them in the same geographic location or at the same time; allowing the sharing of all types of media and documents; and providing tools to assess student performance. To take advantage of all of these benefits, large institutions are investing in MOOCs platforms to monetize their method, making MOOCs available in several languages and disciplines. Because of the high attrition rate observed on many MOOC platforms, dropout prediction, or identifying students at risk of dropping out of a course, is an essential topic to study. By regarding dropout prediction as a sequence classification problem, we propose comparison classification models for solving it., based on machine learning algorithms. In particular, based on the KNearest Neighbor Classification method, Support Vector Machines (SVM), and Logistic Regression (LR), Ada Boost and Random Forest.