Background similarities as a way to predict students' behaviour

Abstract

The number of students opting for online educational platforms has been on the rise in recent years. Despite the upsurge, student retention is still a challenging task, with some students recording low-performance margins on online courses. This paper aims to predict students' performance and behaviour based on their online activities on an e-learning platform. The paper will focus on the data logging history and utilise the learning management system (LMS) data set that is available on the Sakai platform. The data obtained from the LMS will be classified based on students' learning styles in the e-learning environment. This classification will help students, teachers, and other stakeholders to engage early with students who are more likely to excel in selected topics. Therefore, clustering students based on their cognitive styles and overall performance will enable better adaption of the learning materials to their learning styles. The model-building steps include data preprocessing, parameter optimisation, and attribute selection procedures.