<![CDATA[On-time graduation (OTG) is a primary key performance indicator (KPI) for higher education institutions. Delays in graduation adversely affect institutional academic efficiency and increase student costs. This study aims to implement the Support Vector Machine (SVM) algorithm, a machine learning technique, to develop a predictive model for students' on-time graduation. This study employed a quantitative approach using a historical dataset of 20 students as a case study. Five predictor variables were utilized: Semester 4 GPA, total completed credits, attendance percentage, working status, and organizational activity. The dataset was partitioned into 80% for training and 20% for testing. Model performance was evaluated using a Confusion Matrix, along with Accuracy, Precision, Recall, and F1-Score metrics. The evaluation on the test set demonstrated that the SVM model achieved an overall Accuracy of 75%. Specifically for the 'On-Time' class, the model yielded a Precision of 66.7%, a Recall of 100%, and an F1-Score of 80%. These findings suggest that SVM is a viable method and holds potential as an early detection tool to identify students at risk of delayed graduation, thereby enabling timely intervention.]]>
Copyrights © 2025
