Predicting MOOC Dropout over Weeks Using Machine Learning Methods

Abstract

With high dropout rates as observed in many current larger-scale online courses, mechanisms that are able to predict student dropout become increasingly important. While this problem is partially solved for students that are active in online forums, this is not yet the case for the more general student population. In this paper, we present an approach that works on click-stream data. Among other features, the machine learning algorithm takes the weekly history of student data into account and thus is able to notice changes in student behavior over time. In the later phases of a course (i.e., once such history data is available), this approach is able to predict dropout significantly better than baseline methods.

Finding out Reasons for Low Completion in MOOC Environment: An Explicable Approach Using Hybrid Data Mining Methods

“…The prediction task was performed by the integrated predictor and evaluated by precision and recall as indicators. Similar researches are also done [5][6][7][8].…”

The Challenges of Creating Successful Collaborative Working and Learning Activities in Online Engineering Courses

“…This is longer than most MOOCs and although research tells us that this is a long time for a MOOC, and the longer the MOOC, the higher the dropout rate [44], it was necessary to complete all the requirements of the course. The MOOC course was broadly divided into two parts.…”

A Comparative Analysis of Selected Studies in Student Performance Prediction

“…Studies that utilise such platforms to provide predictions at several intervals of a course include [35], [36], [15]. These studies serve as evidence that static data can be done away with when predicting progress, without affecting prediction performance.…”

“…Other activities that may be used as features for building MOOC dropout prediction models include number of video lecture downloads, number of completed quizzes, number of completed tasks, click-stream data, the amount of time spent on course modules and the number of days students are active ( [47], [25], [36], [35], [47], [48], [49], [50]). …”