Multi-Category Prediction of Students’ Academic Performance Using Machine Learning: For Students Joining Higher Educational Institutions in Ethiopia

Abstract Following the deployment of the Learning Management System (LMS) platform in higher educational institutions in Ethiopia, a massive amount of potentially helpful but as-yet untapped educational data has been generated. Despite the fact that the data is powerful enough to contribute to reducing student dropout rates through the application of modern educational data mining techniques such as machine learning, it has not been successfully employed to tackle student academic performance problems in higher education institutions(HEIs). As a result, a machine learning model was proposed based on data from three semesters of undergraduate students at Bule Hora University. To predict students' academic achievement, five machine learning methods (SVM, Random Forest, KNN, Gradient Boosting, and Decision Tree) were used. The Decision Tree model outperformed other models with a promising result of 97.3% on test accuracy and was selected as a proposed model. Moreover, our findings suggest that academic factors (entrance result, study time, attendance, and Internet access) and socio-demographic factors (age, gender, father job, mother job, family size, and address) had a greater impact on students' academic success. However, the academic performance of students was less affected by additional features like extra classes, another job, and guidance and counselling. Moreover, we are working on improving the accuracy of the proposed model. In this study, the student entrance result is the only variable used from the pre-university data. However, a CGPA result is not sufficient to qualify a student. Therefore, in the future, the exit exam results of the students will be incorporated.