<![CDATA[The rapid advancement of data-driven education has enabled schools to utilize machine learning to identify factors influencing student success. This study presents the development and implementation of a web-based Gradient Boosting Machine (GBM) model for classifying student success data at Muhammadiyah Elementary School in East Medan. The proposed system aims to assist educators in evaluating student performance through predictive analytics that integrates academic, behavioral, and attendance data. The research methodology includes data preprocessing, feature selection, and model training using the GBM algorithm due to its robustness in handling non-linear relationships and reducing classification errors through iterative boosting. The web-based application is designed with an interactive interface, allowing teachers and administrators to input, analyze, and visualize student performance patterns easily. The evaluation results indicate that the GBM model achieves high classification accuracy, outperforming traditional algorithms such as Decision Tree and Logistic Regression. This system not only provides accurate predictions of student performance levels but also generates actionable insights for improving learning outcomes and academic interventions. The research contributes to the integration of machine learning and educational management by demonstrating how predictive modeling can be operationalized in real-time through a web-based platform to support data-informed decision-making in Muhammadiyah schools.]]>
