DEVELOPING A PREDICTIVE MODEL FOR CLASSIFYING STUDENT ACCADEMIC PERFORMANCE

ABSTRACT The accurate classification of student performance is crucial for the designing effective interventions to enhance leaning outcomes and support students at risk of underperforming. This study aims to develop a predictive model for classifying student academic performance based on a comprehensive dataset of academic, demographic, and behavioral factors. Leveraging machine learning algorithm, the model integrates variables such as attendance, assignment completion rates, prior academic achievements, and socio-economic indicators to identify patterns and predict outcomes. The research explores multiples classification techniques, including decision trees, support vector machines, and neural networks, to determine the most effective approach. Evaluation metrics such as accuracy, precision, recall, and F1-Score are employed to validate the model’s performance. The findings demonstrate the potential of predictive analytics to assist educators in proactively addressing academic challenges and fostering a data driven approach to student success. Future work focuses on refining the model by incorporating real-time data and expanding its applicability across diverse educational contexts.