<![CDATA[Timely graduation is an important indicator of academic success, particularly for students with disabilities who may require additional academic support. This study aims to predict timely graduation among students with disabilities at Universitas Pamulang using historical academic data and to compare the performance of Decision Tree and Random Forest algorithms. The study employed a quantitative approach and data mining methods using data from 125 students, with 100 records used for training and 25 records for testing. The prediction models were developed using academic variables, including semester GPA, cumulative GPA, total credits earned, study duration, attendance, and disability-related variables. Model performance was evaluated using accuracy, precision, recall, F1-score, confusion matrix, and 5-fold cross-validation. The results showed that Random Forest outperformed Decision Tree in terms of testing accuracy, achieving 88.00% compared with 80.00%. Random Forest also achieved a 5-fold cross-validation accuracy of 97.00% ± 0.0245. Feature importance analysis indicated that IPS_S4, IPS_S3, and AVG_IPS were among the most influential variables. These findings suggest that Random Forest can serve as a supporting tool for the early identification of students who may be at risk of delayed graduation and can help inform data-driven academic interventions.]]>
Copyrights © 2026
