LEVERAGING MACHINE LEARNING TO PREDICT THE IMPACT OF DEMOGRAPHIC AND SOCIO-ECONOMIC FACTORS ON JAMB EXAM OUTCOMES

This project focuses on analyzing the factors that influence student performance in the Joint Admissions and Matriculation Board (JAMB) examination in Nigeria, with the goal of supporting educational planning, The study applies supervised machine learning techniques to predict academic performance based on key demographic and Socio-economic variables. A dataset of 5000 student records was cleaned, preprocessed and used to develop four predictive models; Support Vector Machine, Decision Tree, Random Forest and Gradient Boosting Tree. Each model was evaluated using performance metrics such as accuracy, precision, recall and F1-score. The Random Forest and the Gradient Boosting model achieved the highest accuracy of 73%, demonstrating their effectiveness in predicting student outcomes. The result shows outcomes such as study hours and distance to school have significant impact on student performance. This research highlights the value of using data-driven approach to identity students who may be at risk of underperforming and to guide educators and policy makers in designing targeted intervention. The findings contributed to the field of educational analytics by demonstrating how predictive modeling can inform strategies to improve student outcomes in standardized examinations.