One of the major challenges of academic institutions is the student dropout rate. It negatively impacts students, universities, and society by precluding student success, wasting time and financial resources, and reducing graduation rates. Previous studies have used machine learning (ML), deep learning (DL), and explainable artificial intelligence (XAI) techniques to predict dropout. However, most of these studies focused primarily on academic factors and were often limited to a single educational institution. Although national reports indicate that 40% to 50% of university students in Saudi Arabia do not complete their programs, few studies have examined dropout at various universities in the country or considered a broader set of factors. Therefore, this research aims to develop predictive models for academic dropout in Saudi universities using ML and DL techniques, taking into account various academic, personal, social, and cultural factors. Data were collected from 4,560 students and then processed and analyzed using twelve feature selection-based learning models. Shapley Additive Explanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) were used as XAI models to identify the most influential features, including GPA, academic year, employment status, family/friends support, and prior major knowledge. The results indicate that the K-Nearest Neighbors (KNN)-based Recursive Feature Elimination (RFE) model achieves the best performance, with an accuracy of 97.6%. Additionally, the Local Explanation Evaluation Framework (LEAF) showed that LIME outperformed SHAP on all four metrics: fidelity, local concordance, prescriptivity, and stability. These findings provide insights into the key factors influencing student dropout at Saudi universities and support the development of early intervention strategies.
Albugami et al. (Tue,) studied this question.