Application of Random Forest Classification Algorithm in Predicting Information Technology Students’ Progression in Tertiary Education

The study applied the Random Forest classification algorithm to predict the progression of Information Technology (IT) students in tertiary education. The dataset used for this study consisted of students' demographic and academic information, such as gender, age, socio-economic status, and grades. Also, the study aimed to identify the influencing factors that affect student attrition in IT programs and provide intervention programs to combat attrition. The results of the analysis showed that the Random Forest model had an accuracy of 95.6% in predicting student progression. Additionally, the study found that factors such as students' grades and socio-economic status significantly impacted their likelihood of progressing. The study recommends an intervention program aimed at reducing student attrition, which includes early identification of at-risk students, provision of academic advising, mentoring, and targeted support services like tutoring, and financial aid. The study highlights the potential of using machine learning techniques such as the Random Forest Model to inform and improve student retention strategies in IT programs.