Leveraging Ensemble Learning for Predicting Student Graduation: A Data Mining Approach

Abstract

Predicting student graduation status is crucial for educational institutions in assessing student progress and improving academic outcomes. This study explores the application of ensemble machine learning techniques to classify and predict the graduation status of students at Klabat University. By combining multiple machine learning algorithms such as Random Forest, Gradient Boosting, and Bagging, the ensemble approach aims to enhance prediction accuracy and robustness compared to individual models. The research utilizes historical academic data, including GPA, attendance, and other relevant variables, to train the models. The results indicate that ensemble methods outperform single classifiers in terms of precision, recall, and overall accuracy, making them a viable solution for predicting student success and informing academic interventions. This study contributes to the growing field of educational data mining by demonstrating the potential of machine learning for improving institutional decision-making and student outcomes.