Student Retention Risk Prediction Using Machine Learning and Educational Analytics

Student retention is a major challenge faced by educational institutions worldwide. Early identification of students who are at risk of academic failure or dropout enables institutions to provide timely interventions and improve student success rates. This research proposes a machine learning-based system for predicting student academic risk using historical academic data. The system analyzes key academic attributes including attendance percentage, semester grade point averages, backlog count, and student participation in events. A Random Forest Regression model is used to estimate a risk probability score for each student. The predicted score is then used to classify students into low-risk, medium-risk, and high-risk categories. The system also includes an interactive dashboard that visualizes student risk patterns and highlights at-risk students for early intervention. Experimental results demonstrate that the proposed model achieves high predictive accuracy with strong generalization capability. The developed system provides a practical decision-support tool for educational institutions to monitor student performance and improve retention outcomes through data-driven strategies.