Covid-19 pandemic has caused many obstacles to higher education students, especially students with academic, financial, and family disadvantages. Moreover, Covid-19 has caused negative impacts on enrollment of junior students and students’ academic goals, which has led to a higher rate of dropouts worldwide.
University enrollment is a complex process for students and families, and the decision to drop out is overwhelming to both. Many factors might cause the dropout, but the most important factors that might affect this decision are financial factors and academic standing. Higher education institutions can boost their academic advising plans, through the use of their strategic resources of data and Machine Learning techniques.
This study investigated the important factors that influence students' dropout and also studied the factors that indicate that a particular student needs extra academic advising.
This study used two datasets, and different machine learning algorithms. For the dropout prediction, the K-Nearest Neighbor model outperformed the Random Forest and the Decision tree models. While for the extra advising prediction, the Random Forest model outperformed the Decision tree and the Artificial Neural Network models.
The study found that Tuition fees status and age at enrollment seriously affect student decision of drop out. Also, the study found that academic standing, year of study, and special needs cases are the most factors that indicate if a student needs extra academic advising.
Professional Studies (MS)
Department, Program, or Center
Graduate Programs & Research (Dubai)
Abuzayeda, Reem, "Effective Academic Advising Strategy in Higher Education using Machine Learning" (2022). Thesis. Rochester Institute of Technology. Accessed from