Predicting MOOC Dropout over Weeks Using Machine Learning Methods

TLDR

High dropout rates in large-scale online courses make predicting student dropout increasingly important, yet solutions are limited to active forum participants and not the broader student population. The paper proposes a click‑stream‑based approach to predict student dropout. The method uses machine‑learning on click‑stream data, incorporating weekly student history to detect behavioral changes. In later course phases, the approach predicts dropout significantly better than baseline 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.