DEVELOPMENT OF A MACHINE LEARNING ALGORITHM FOR STUDENT PERFORMANCE PREDICTION

ABSTRACT This study investigates the application of machine learning techniques to predict student performance and facilitate early intervention in educational settings. By analyzing a comprehensive dataset comprising academic records, demographic information, and behavioral indicators, we develop and evaluate various predictive models,. The objective is to identify students at risk of academic underperformance early in their academic journey, enabling timely interventions and personalized support. We assess the models' performance using metrics such as accuracy, precision, and recall. Furthermore, we explore feature importance to understand the key factors influencing student performance. The results demonstrate the potential of machine learning to accurately predict student outcomes and inform the development of effective early intervention strategies, ultimately contributing to improved student success and retention.