Klasifikasi Mahasiswa Berpotensi Drop Out (DO) Menggunakan Algoritma Random Forest

Student dropout is a serious problem that affects the quality of graduates and the reputation of higher education institutions. Student dropout is a serious challenge in higher education institutions, including Bengkalis State Polytechnic, which recorded 198 cases of dropout. This study aims to develop a classification system for students at risk of dropping out using the Random Forest algorithm based on academic and non-academic data. The Rapid Application Development (RAD) method was used in the system development, with a dataset of 398 students and nine research attributes, namely Gender, Length of Study, Violations, GPA, Absence, Parental Income, Leave and Registration History, KIP Status, and Place of Residence. The evaluation results showed an accuracy of 97%, precision of 98%, and recall of 97%. The early warning feature successfully identified 49 students out of 200 active students (24%) from the total data used as potentially dropping out. These results indicate that the Random Forest algorithm can be used as a measurable and data-based classification system for students who are potentially
dropping out.