PREDICTING STUDENT DROPOUT RISK USING MACHINE LEARNING IN HIGHER EDUCATION

Authors

  • Khalilova Sarvinoz Author
  • Lochinbek Boboev Author

Keywords:

Student Dropout, Educational Data Mining, Machine Learning, Predictive Analytics, Higher Education, Uzbekistan.

Abstract

This article examines the application of machine learning methods for the early prediction of student dropout risk at higher education institutions in Uzbekistan. The relevance of the study lies in the fact that low academic performance, financial
difficulties, and socio-psychological factors lead many students to leave their studies, while university administrations typically become aware of this only after the student has already withdrawn, resulting in a missed opportunity for timely
intervention. To address this problem, the article proposes a predictive model based on the Random Forest, Logistic Regression, and XGBoost algorithms that analyzes students' attendance, midterm grades, LMS platform activity, and sociodemographic indicators to identify students at high risk of dropout in advance. Thestudy describes the structure of the dataset, a three-stage (semester-wise)  prediction process, and a comparative analysis of the models based on Accuracy, Precision, and Recall metrics. The expected results indicate that XGBoost and Random Forest achieve the highest predictive accuracy, enabling universities to provide timely financial and academic support to at-risk students.

References

1. Romero, C., Ventura, S. (2010). Educational Data Mining: A Review of the Stateof-the-Art. IEEE Transactions on Systems, Man, and Cybernetics, Part C:

Applications and Reviews, 40(6), 601–618.

https://www.researchgate.net/publication/224160756_Educational_Data_Minin

g_A_Review_of_the_State_of_the_Art

2. Romero, C., Ventura, S. (2020). Educational data mining and learning analytics:

An updated survey. WIREs Data Mining and Knowledge Discovery, 10(3),

e1355. https://wires.onlinelibrary.wiley.com/doi/abs/10.1002/widm.1355

3. Krüger, J. G. C., de S. Britto, A., Barddal, J. P. (2023). An explainable machine

learning approach for student dropout prediction. Expert Systems with

Applications, 233, 120933. https://doi.org/10.1016/j.eswa.2023.120933

4. Marquez-Vera, C., Morales, C. R., Soto, S. V. (2013). Predicting School Failure

and Dropout by Using Data Mining Techniques. IEEE Revista Iberoamericana

de Tecnologias del Aprendizaje, 8(1), 7–14.

https://doi.org/10.1109/RITA.2013.2244695

5. Aldowah, H., Al-Samarraie, H., Alzahrani, A. I., Alalwan, N. (2020). Factors

affecting student dropout in MOOCs: a cause and effect decision-making model.

Journal of Computing in Higher Education, 32(2), 429–454.

https://link.springer.com/article/10.1007/s12528-019-09241-y

6. Student Dropout Prediction Using Random Forest and XGBoost Method.

INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi,

2025. https://ojs.unpkediri.ac.id/index.php/intensif/article/view/21191

7. Predicting Student Dropout in Higher Education Using Machine Learning

Techniques: A Predictive Model Using XGBoost Algorithm. ResearchGate,

2024.

https://www.researchgate.net/publication/386564297_Predicting_Student_Drop

out_in_Higher_Education_Using_Machine_Learning_Techniques_A_Predictiv

e_Model_Using_XGBoost_Algorithm

8. Machine Learning Models for Predicting Student Dropout, Continued Enrollment

and Graduation (Multinomial Logistic Regression, Random Forest, XGBoost).

Preprints.org, 2025.

https://www.preprints.org/frontend/manuscript/534d2effd7ea0040a8ea024b670

f0033/download_pub

9. Predicting student dropouts with machine learning: An empirical study in Finnish

higher education. International Journal of Educational Research, ScienceDirect,

2024. https://www.sciencedirect.com/science/article/pii/S0160791X24000228

10. Student dropout prediction through machine learning optimization: insights from

Moodle log data. Scientific Reports (Nature), 15, 2025.

https://www.nature.com/articles/s41598-025-93918-1

11. SentiDrop: A Multi Modal Machine Learning model for Predicting Dropout in

Distance Learning. arXiv preprint, 2025. https://arxiv.org/pdf/2507.10421

12. Chung, J. Y., Lee, S. (2019). Dropout early warning systems for high school

students using machine learning. Children and Youth Services Review, 96, 346–

353. https://doi.org/10.1016/j.childyouth.2018.11.030

13. Uzbekistan's strategy for the development of artificial intelligence technologies

until 2030. Digital Watch Observatory, 2025.

https://dig.watch/resource/uzbekinstans-strategy-for-the-development-ofartificial-intelligence-technologies-until-2030

14. The Future of Higher Education in Uzbekistan: The Potential and Challenges of

Integrating Artificial Intelligence (National Survey). Perspectives of Higher

Education Development, 2025.

https://erasmus.uz/journal/index.php/files/article/view/129

Published

2026-08-02