Predicting MOOCs Dropout Using Only Two Easily Obtainable Features from the First Week's Activities

TL;DR

This paper demonstrates that using only two easily obtainable features from the first week of activities, machine learning models can predict MOOC dropout with high accuracy, outperforming more complex approaches.

Contribution

It introduces a simple early prediction method for MOOC dropout using just two features, achieving superior accuracy compared to existing methods.

Findings

Achieved 82%-94% prediction accuracy with two features.

Outperformed state-of-the-art approaches with more features.

Validated effectiveness across multiple machine learning classifiers.

Abstract

While Massive Open Online Course (MOOCs) platforms provide knowledge in a new and unique way, the very high number of dropouts is a significant drawback. Several features are considered to contribute towards learner attrition or lack of interest, which may lead to disengagement or total dropout. The jury is still out on which factors are the most appropriate predictors. However, the literature agrees that early prediction is vital to allow for a timely intervention. Whilst feature-rich predictors may have the best chance for high accuracy, they may be unwieldy. This study aims to predict learner dropout early-on, from the first week, by comparing several machine-learning approaches, including Random Forest, Adaptive Boost, XGBoost and GradientBoost Classifiers. The results show promising accuracies (82%-94%) using as little as 2 features. We show that the accuracies obtained outperform state of the art approaches, even when the latter deploy several features.