From Data to Decision: Machine Learning and Explainable AI in Student Dropout Prediction

Student dropout is a critical issue with diverse consequences for the success of students, universities, and society. By delving into the factors behind dropout rates and leveraging predictive methodologies, universities and policymakers can develop targeted interventions to reduce dropout rates. Despite the progress in this area, limitations remain, including narrow research scopes, a reliance on traditional academic factors, and limited integration of qualitative perspectives. This paper highlights these gaps and provides actionable recommendations for future research, such as incorporating explainable AI, expanding sample populations, and integrating diverse factors like psychological health and cultural influences.