On the Use of Bayesian Probabilistic Matrix Factorization for Predicting Student Performance in Online Learning Environments

Abstract

Thanks to the advances in digital educational technology, online learning (or e-learning) environments such as Massive Open Online Course (MOOC) have been rapidly growing. In the online educational systems, however, there are two inherent challenges in predicting performance of students and providing personalized supports to them: sparse data and cold-start problem. To overcome such challenges, this article aims to employ a pertinent machine learning algorithm, the Bayesian Probabilistic Matrix Factorization (BPMF) that can enhance the prediction by incorporating background information on the side of students and/or items. An experimental study with two prediction settings was conducted to apply the BPMF to the Statistics Online data. The results shows that the BPMF with using side information provided more accurate prediction in the performance of both existing and new students on items, compared to the algorithm without using any side information. When the data are sparse, it is demonstrated that a lower dimensional solution of the BPMF would benefit the prediction accuracy. Lastly, the applicability of the BPMF to the online educational systems were discussed in the context of educational assessment.