Search Results

ABSTRACT

The increasing reliance on the learning management system (LMS) in this era of digital education offers a vital source of student data that can be leveraged to predict student academic progress. Predicting student academic progress in higher education (HE) supports timely intervention and enhances student retention. This study develops and compares multiple machine learning (ML) and deep learning (DL) models to identify at-risk students based on students’ interaction data with LMS by leveraging an integrated DSR methodology. Multiple predictive models are developed by incorporating data augmentation and balancing techniques to address class imbalance and enhance the accuracy of the predictive model. The study compares ten different models to achieve the highest classification accuracy in predicting students at risk of failing through the integration of through the integration of both ML and DL algorithms, including random forest, decision tree, convolutional neural networks, multi-layer perceptron, and long short-term memory (LSTM). The comparison results unscored the value of the DL based predictive model in the HE setting to precisely predict student academic performance, particularly the LTSM based model, which has the highest and nearly perfect accuracy. The existing LMS systems can incorporate this DL based predictive model to provide educational stakeholders with benefits and insights that support students’ academic journeys and institutional success.

Keywords: machine learning, deep learning, design research, higher education, LMS data, student academic progress