Enhancing learner performance prediction on online platforms using machine learning algorithms

Abstract

E-learning has emerged as a prominent educational method, providing accessible and flexible learning opportunities to students worldwide. This study aims to comprehensively understand and categorize learner performance on e-learning platforms, facilitating timely support and interventions for improved academic outcomes. The proposed model utilizes various classifiers (random forest (RF), neural network (NN), decision tree (DT), support vector machine (SVM), and K-nearest neighbors (KNN)) to predict learner performance and classify students into three groups: fail, pass, and withdrawn. Commencing with an analysis of two distinct learning periods based on days elapsed (≤120 days and another exceeding 220 days), the study evaluates the classifiers’ efficacy in predicting learner performance. NN (82% to 96%) and DT (81%-99.5%) consistently demonstrate robust performance across all metrics. The classifiers exhibit significant performance improvement with increased data size, suggesting the benefits of sustained engagement in the learning platform. The results highlight the importance of selecting suitable algorithms, such as DT, to accurately assess learner performance. This enables educational platforms to proactively identify at-risk students and offer personalized support. Additionally, the study highlights the significance of prolonged platform usage in enhancing learner outcomes. These insights contribute to advancing our understanding of e-learning effectiveness and inform strategies for personalized educational interventions.