(SAMPLE DATA) Predictive Analytics for Student Academic Performance Using Machine Learning Algorithms in Higher Education

Authors

Abstract

This study investigates the application of machine learning algorithms—specifically Random Forest, Support Vector Machine, and Gradient Boosting—to predict academic performance of university students in the Philippines. Using a dataset of 1,200 undergraduate students over three academic years, the study identified key predictors including attendance rate, midterm grades, and socioeconomic indicators. Random Forest achieved the highest accuracy at 87.3%, enabling early intervention programs. The findings suggest that data-driven approaches can substantially reduce dropout rates and improve institutional effectiveness in higher education settings.

Keywords