Applying machine learning approach to predict students’ performance in higher educational institutions
Abstract
Purpose – Academic success and failure are relevant lifelines for economic success in the knowledge-based economy. The purpose of this paper is to predict the propensity of students’ academic performance using early detection indicators (i.e. age, gender, high school exam scores, region, CGPA) to allow for timely and efficient remediation. Design/methodology/approach – A machine learning approach was used to develop a model based on secondary data obtained from students’ information system in a Nigerian university. Findings – Results revealed that age is not a predictor for academic success (high CGPA); female students
are 1.2 times more likely to have high CGPA compared to their male counterparts; students with high JAMB scores are more likely to achieve academic success, high CGPA and vice versa; students from affluent and
developed regions are more likely to achieve academic success, high CGPA and vice versa; and students in Years 3 and 4 are more likely to achieve academic success, high CGPA. Originality/value – This predictive model serves as a classifier and useful strategy to mitigate failure, promote success and better manage resources in tertiary institutions.