HYBRID PREDICTIVE MODEL FOR STUDENTS’ ACADEMIC PERFORMANCE BASED ON MACHINE LEARNING APPROACH

Student academic performance is a critical factor in assessing the quality of education and institutional effectiveness. Various factors, including socioeconomic background, institutional policies, prior academic achievement, and learning environments, contribute to student success. Understanding these factors is essential for developing targeted interventions to improve academic outcomes. This research investigates the factors influencing student academic performance at Umaru Ali Shinkafi Polytechnic through the development and implementation of a hybrid prediction model. By drawing on diverse data sources and advanced analytical techniques, the study aims to uncover the complex interplay of school factors, prior academic achievement, and other relevant variables shaping student outcomes. Utilizing a stratified random sampling technique, data was collected from a population of students at the institution. A hybrid prediction model incorporating linear regression, decision trees, and random forests was developed and evaluated on a test dataset consisting of 254 records. The model achieved an accuracy of 0.85, a precision of 0.82, a recall of 0.88, an F1-score of 0.85, and an ROC-AUC score of 0.91. These results indicate that the hybrid model outperforms benchmark techniques, providing robust predictive performance and significant insights into the factors affecting student success. These findings offer actionable recommendations for educators, policymakers, and stakeholders to enhance educational strategies and support student achievements.