|
A Machine Learning Model for Investigating the Causes Influencing Student Dropout and Predicting Student Performance
|
Kiarash Zohori1   , Marjan Fallah2 |
1- Department of Toxicology and Pharmacology, Faculty of Pharmacy, Ayatollah Amoli Branch, Islamic Azad University, Amol, Iran , arieltehrani77@gmail.com
2- Department of Toxicology and Pharmacology, Faculty of Pharmacy, Ayatollah Amoli Branch, Islamic Azad University, Amol, Iran |
|
|
Abstract: (31 Views) |
Introduction: Identifying students at risk of dropping out is crucial for providing timely support, improving retention rates, and ensuring academic success. Machine learning can be employed to analyze patterns in student behavior, enabling universities to predict dropouts and take preventive measures for effective intervention.
Methods: A combination of Particle Swarm Optimization and Extreme Gradient Boosting algorithms was used to create a classifier model. Data analysis methods were also employed to analyze and examine the data and extract useful insights.
Results: The proposed model demonstrated an accuracy of 98.12%, which is higher than other models. It was also shown that academic data are more influential variables in student dropout decisions. Students who failed to pay their tuition on time were significantly more at risk of dropping out (87.05%) and had a lower likelihood of graduation (4.95%) compared to students who paid their tuition on time, who had a lower dropout rate (25.21%) and a higher graduation rate (55.13%). Additionally, dropout rates increase with age for both genders, although women consistently show lower dropout rates across all age groups.
Conclusion: By utilizing machine learning to predict dropout risks, institutions can allocate their resources more effectively to support students in completing their education. |
|
| Keywords: Machine learning, Metaheuristics, Student dropout, Decision-making |
|
|
|
Type of Article: Research Article |
Subject:
Health Management
Received: 2025/03/21 | Revised: 2025/09/15 | Accepted: 2025/09/15
|
|
|
|
|
|
|
| Send email to the article author |
|
|
