<![CDATA[The issue of graduation delay is one of the common issue in higher education institutions. This issue impacts the accreditation and reputation of study programs and the university. Delayed graduation increases the likelihood of student dropout, which remains a pressing concern many universities in Indonesia. The resulting consequences include a decline in institutional reputation and ranking, as well as reduced public trust in higher education standards. This research seeks to create a predictive model for delays in student graduation at University XYZ utilizing three machine learning techniques: Decision Tree, Random Forest, and Gradient Boosting. The academic dataset displays a class imbalance, with a notably larger number of students graduating later than those graduating on time. To counter this issue, the Adaptive Synthetic Sampling (ADASYN) method was implemented. The findings indicate that Random Forest with ADASYN achieves the best performance, with an accuracy of 75.55%, precision of 82.15%, recall of 81.64%, and AUC of 82.96%. The most influential factors are GPA (IPK) and the number of course repetitions. The resulting model can serve as a foundation for an early warning system to support universities in implementing timely academic interventions for at-risk students.]]>
Copyrights © 2026
