Educational data mining plays a crucial role in analyzing student performance to identify those at risk and enhance academic success. Traditional statistical methods often fail to capture the complex factors influencing student achievement. This research presents a machine learning-based predictive system integrated into a web application to forecast student academic performance. The study utilizes a dataset from Taraba State University, comprising students from diverse demographics. The dataset undergoes preprocessing, feature selection, and modeling using three machine learning algorithms: Random Forest, Support Vector Machine (SVM), and Decision Tree. The evaluation results demonstrate that Random Forest achieved the highest accuracy (94%), followed by SVM (93%) and Decision Tree (92%). The developed web-based system allows educators to input student data and receive real-time performance predictions, facilitating early intervention strategies. The study highlights the potential of machine learning in educational decision-making and recommends further research on ensemble learning techniques for real-time academic performance prediction.
Anagu et al. (Wed,) studied this question.