International Journal of Scientific Research and Engineering Development

Early identification of at-risk students is a critical challenge in academic institutions seeking to improve student retention and outcomes. Traditional approaches to monitoring student performance rely on manual assessment, which is often subjective and fails to capture the complex interplay of factors affecting academic risk. This paper presents the development of an early warning system for at-risk students using performance analytics and machine learning models. The proposed system employs classification models including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and XGBoost to analyze student academic data. The system evaluates student risk based on key indicators such as assignment completion rates, attendance, assessment scores, and engagement levels, and classifies each student into High-Risk, Medium-Risk, and Low-Risk categories. The proposed early identification system enables timely academic interventions, reduces manual monitoring effort, and improves the reliability of the at-risk identification process.

T.Thirunavukarasu, P.Logaiyan,"Early Identification of At-Risk Students Using Machine Learning" International Journal of Scientific Research and Engineering Development, V9(3): Page(2158-2163) May-June 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.