Machine learning approach of predicting learning outcomes of MOOCs to increase its performance

Abstract

Accumulated statistics on the activity of MOOC’s students allow to predict their future behavior and learning outcomes. This article suggests a hypothesis about the possibility of predicting a fact of passing an exam by a student using his activity in the first half of the course. To solve this problem, various machine learning approaches and models have been proposed. According to the results, the most significant features were obtained for assessing the fact that the exam was passed by the students. As a result of model’s prediction, a list of participants was received. We offer to put an additional impact on these students to improve their performance of learning in the course.