A Study on Dropout Prediction for University Students Using Machine Learning
Source abstract
Abstract
Student dropout is a serious issue in that it not only affects the individual students who drop out but also has negative impacts on the former university, family, and society together. To resolve this, various attempts have been made to predict student dropout using machine learning. This paper presents a model to predict student dropout at Sahmyook University using machine learning. Academic records collected from 20,050 students of the university were analyzed and used for learning. Various machine learning algorithms were used to implement the model, including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, Deep Neural Network, and LightGBM (Light Gradient Boosting Machine), and their performances were compared through experiments. We also discuss the influence of oversampling used to resolve data imbalance issues in the dropout data. For this purpose, various oversampling algorithms such as SMOTE, ADASYN, and Borderline-SMOTE were tested. Our experimental results showed that the proposed model implemented using LightGBM provided the best performance with an F1-score of 0.840, which is higher than the results of previous studies discussing the dropout prediction with the issue of class imbalance.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Online Learning and Analytics · Anomaly Detection Techniques and Applications · Artificial Intelligence in Healthcare
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Division of Computer Science and Engineering, Sahmyook University, Hwarangro 815, Seoul 01795, Republic of Korea
Department of Digital Contents Design, Ulsan College, Ulsan 44610, Republic of Korea
Funding
Sahmyook University Research Fund
References (40)
Show source-provided references
1. Kim, D., and Kim, S. (2018). Sustainable education: Analyzing the determinants of university student dropout by nonlinear panel data models. Sustainability, 10.10.3390/su10040954 ↗
2. Martinho, V.R.D.C., Nunes, C., and Minussi, C.R. (2013, January 4–6). An intelligent system for prediction of school dropout risk group in higher education classroom based on artificial neural networks. Proceedings of the 2013 IEEE 25th International Conference on Tools with Artificial Intelligence, Washington, DC, USA.10.1109/ICTAI.2013.33 ↗
3. Machine learning assisted hepta band THz metamaterial absorber for biomedical applications10.1038/s41598-023-29024-x ↗
4. Multiband Metamaterial absorber with absorption prediction by assisted machine learning10.1016/j.matchemphys.2023.128180 ↗
5. A survey of machine learning approaches for student dropout prediction in online courses10.1145/3388792 ↗
6. Predicting academic success in higher education: Literature review and best practices10.1186/s41239-020-0177-7 ↗
7. A Survey of Machine Learning Approaches and Techniques for Student Dropout Prediction10.5334/dsj-2019-014 ↗
8. Kim, S., Choi, E., Jun, Y.K., and Lee, S. (2023). Student Dropout Prediction for University with High Precision and Recall. Appl. Sci., 13.10.3390/app13106275 ↗
9. A study on the development of university students dropout prediction model using classification technique
10. Development of prediction model to improve dropout of cyber university
11. Onah, D.F., Sinclair, J., and Boyatt, R. (2014, January 7–9). Dropout rates of massive open online courses: Behavioral patterns. Proceedings of the 6th International Conference on Education and New Learning Technologies, Barcelona, Spain.
12. Liyanagunawardena, T.R., Parslow, P., and Williams, S. (2014, January 10–12). Dropout: MOOC participants’perspective. Proceedings of the EMOOCs 2014, the Second MOOC European Stakeholders Summit, Lausanne, Switzerland.
13. Dropout prediction in MOOCs: Using deep learning for personalized intervention10.1177/0735633118757015 ↗
14. Ridge regression10.1002/wics.14 ↗
15. Induction of decision trees10.1007/BF00116251 ↗
16. Ho, T.K. (1995, January 14–16). Random Decision Forests. Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, QC, Canada.
17. Support vector machines
18. Deep learning in neural networks: An overview10.1016/j.neunet.2014.09.003 ↗
19. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.Y. (2017, January 4–9). LightGBM: A highly efficient gradient boosting decision tree. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.
20. SMOTE: Synthetic minority over-sampling technique10.1613/jair.953 ↗
21. He, H., Bai, Y., Garcia, E.A., and Li, S. (2008, January 1–8). ADASYN: Adaptive synthetic sampling approach for imbalanced learning. Proceedings of the 2008 IEEE International Joint Conference on Neural Networks, Hong Kong, China.
22. Han, H., Wang, W.-Y., and Mao, B.-H. (2005, January 23–26). Borderline-SMOTE: A new over-sampling method in imbalanced data sets learning. Proceedings of the IEEE 2005 International Conference on Advances in Intelligent Computing, Hefei, China.10.1007/11538059_91 ↗
23. Predictive Models for Imbalanced Data: A School Dropout Perspective10.3390/educsci9040275 ↗
24. Roughly balanced bagging for imbalanced data10.1002/sam.10061 ↗
25. A study of the behavior of several methods for balancing machine learning training data10.1145/1007730.1007735 ↗
26. Chen, T., and Guestrin, C. (2016, January 13). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
27. Dorogush, A.V., Ershov, V., and Gulin, A. (2018). CatBoost: Gradient boosting with categorical features support. arXiv.
28. Naïve Bayes
29. Da Silva, M., Diogo, E., Solteiro, P., Eduardo, J., Arsénio, R., de Moura, O., Paulo, B., and Barroso, J. (2022). Forecasting Students Dropout: A UTAD University Study. Future Internet, 14.10.3390/fi14030076 ↗
30. A real-life machine learning experience for predicting university dropout at different stages using academic data10.1109/ACCESS.2021.3115851 ↗
31. Greedy function approximation: A gradient boosting machine10.1214/aos/1013203451 ↗
32. Sandoval-Palis, I., Naranjo, D., Vidal, J., and Gilar-Corbi, R. (2020). Early Dropout Prediction Model: A Case Study of University Leveling Course Students. Sustainability, 12.10.3390/su12229314 ↗
33. Shynarbek, N., Orynbassar, A., Sapazhanov, Y., and Kadyrov, S. (2021, January 25–26). Prediction of Student’s Dropout from a University Program. Proceedings of the 16th International Conference on Electronics Computer and Computation (ICECCO), Kaskelen, Kazakhstan.10.1109/ICECCO53203.2021.9663763 ↗
34. (2023, August 28). Exponential Smoothing. Available online: https://en.wikipedia.org/wiki/Exponential_smoothing.
35. (2023, August 28). Seaborn, Statistical Data Visualization. Available online: https://seaborn.pydata.org.
36. (2023, August 28). Scikit-Learn. Available online: https://en.wikipedia.org/wiki/Scikit-learn.
37. (2023, August 28). Keras. Available online: https://www.tensorflow.org/guide/keras.
38. Handling vanishing gradient problem using artificial derivative10.1109/ACCESS.2021.3054915 ↗
39. Lee, S., and Chung, J.Y. (2019). The machine learning-based dropout early warning system for improving the performance of dropout prediction. Appl. Sci., 9.10.3390/app9153093 ↗
40. Early prediction model of student performance based on deep neural network using massive LMS log data