Evaluating Machine Learning Models for Predicting Graduation Timelines in Moroccan Universities

The escalating student numbers in Moroccan universities have intensified the complexities of managing on-time graduation. In this context, Machine learning methodologies were utilized to analyze patterns and predict graduation rates a comprehensive manner. Our dataset comprised information from 5236 bachelor students who graduated years 2020 2021 Faculty Law, Economic, Social Sciences at Moulay Ismail University. incorporated diverse range attributes including age, marital status, gender, nationality, socio-economic category parents, profession, disability province residence, high school diploma attainment, academic honors, all contributing understanding factors influencing outcomes. Implementation evaluation performance five different machine models: Support Vector Machines, Decision Tree, Naive Bayes, Logistic Regression, Random Forest, carried out. These models assessed based on their classification reports, confusion matrices, Receiver Operating Characteristic (ROC) curves. From findings, Forest model emerged as most accurate predicting graduation, showcasing highest accuracy ROC AUC score. Despite these promising results, it is believed that enhancements can be achieved through further tuning preprocessing dataset. Insights study could enable universities, among others, better comprehend implement appropriate measures improve