Predicting student performance using machine learning to enhance the quality assurance of online training via Maharat platform

Abstract

There are multiple entities responsible for online training programs via the Taif Maharat platform at the university. There is a variation in objectives, content, trainers’ efficiency, online interaction and participation patterns, training strategies, evaluation tools, and feedback techniques. In addition, there is a lower achievement of standards in dimensions such as planning and curriculum design, leadership, online learning and training, technology, assessment, student support, continuous improvement, and evaluation. Based on these justifications, the study proposed a Machine Learning (ML) approach, which predicts the student’s performance to enhance the quality assurance of online training programs via the Maharat platform at Taif University based on the online learning training standards in the Kingdom of Saudi Arabia (KSA). The paper's primary objective is to forecast academic achievement by considering their participation in an online learning environment. The relevant feature was extracted using hybrid optimization, and following this classification process was carried out. For the predictions, the Support Vector Machine technique was applied. To identify and determine the degree of achievement of quality assurance of online training programs standards, we used a descriptive-analytical approach to analyze the sample opinions about quality assurance of online training via the Maharat platform at Taif University.

Keywords

• Online training
• Online learning standards
• Quality assurance
• Maharat platform
• Taif University
• Conceptualizing