Prediction of Course Failure in University Students Using Machine Learning Techniques: Comparison of Supervised Models
DOI:
https://doi.org/10.70554/OBJK2026.v02n02.01Keywords:
Machine learning, Decision tree, K-nearest neighbors, Random forest, SMOTE, Cross-validation, Academic failure, Social media, Feature importanceAbstract
The use of digital platforms among Colombian college students continues to grow, and with that, the question of whether it affects retention and academic performance has resurfaced. In Riohacha, this relationship had not been studied using artificial intelligence tools at the institutional level. For this study, a dataset was constructed based on a survey administered to 300 undergraduate students at the University of La Guajira. Twenty-one sociodemographic, behavioral, and digital perception variables were captured and organized using the CRISP-DM methodology. The target variable is binary: whether the student has failed at least one course. Three supervised classification algorithms (Decision Tree, KNN, and Random Forest) were compared, integrated into pipelines with SMOTE and five-fold stratified cross-validation. Random Forest yielded the best results, with 62% accuracy, an F1-Score of 0.606, and an ROC AUC of 0.682. Feature importance analysis identified the level of concentration while studying, daily hours of cell phone use, and preferred social network as the most significant predictors.
References
I. K. Nti and others, “Prediction of social media effects on students’ academic performance using Machine Learning Algorithms (MLAs),” Journal of Computers in Education, vol. 9, no. 2, pp. 195–223, 2022, doi: 10.1007/s40692-021-00192-3. DOI: https://doi.org/10.1007/s40692-021-00201-z
L. Al-Alawi, J. Al Shaqsi, A. Tarhini, and A. S. Al-Busaidi, “Using machine learning to predict factors affecting academic performance: the case of college students on academic probation,” Educ. Inf. Technol. (Dordr)., vol. 28, no. 10, pp. 12407–12432, 2023, doi: 10.1007/s10639-023-11700-0. DOI: https://doi.org/10.1007/s10639-023-11700-0
A. A. Deyser Gutiérrez, J. Fredy Vélez Díaz, and J. M. López, “Indicadores de deserción universitaria y factores asociados,” EducaT: Educación Virtual, Innovación Y Tecnologías, 2021, doi: 10.22490/27452115.4738.
A. D. Solano-barliza, “Quantitative analysis of the perception of using ChatGPT artificial intelligence in the teaching and learning of Colombian-Caribbean undergraduate students,” Formación Universitaria, vol. 17, no. 3, pp. 129–138, 2024. DOI: https://doi.org/10.4067/s0718-50062024000300129
H. Yu, W. Yang, N. Xu, and Y. Du, “Advertising strategy and contract coordination for a supply chain system: immediate and delayed effects,” Kybernetes, vol. 52, no. 1, pp. 235–261, Oct. 2021, doi: 10.1108/K-03-2021-0185. DOI: https://doi.org/10.1108/K-03-2021-0185
S. H. Hemal, M. A. R. Khan, I. Ahammad, M. Rahman, M. A. S. Khan, and S. Ejaz, “Predicting the impact of internet usage on students’ academic performance using machine learning techniques in Bangladesh perspective,” Soc. Netw. Anal. Min., vol. 14, no. 1, p. 66, 2024.
J. Sweller, “Cognitive load during problem solving: Effects on learning,” Cogn. Sci., vol. 12, no. 2, pp. 257–285, 1988, doi: 10.1207/s15516709cog1202_4. DOI: https://doi.org/10.1207/s15516709cog1202_4
J. Sweller, “Cognitive load theory, learning difficulty, and instructional design,” Learn. Instr., vol. 4, no. 4, pp. 295–312, 1994, doi: 10.1016/0959-4752(94)90003-5. DOI: https://doi.org/10.1016/0959-4752(94)90003-5
M. H. Goldhaber, “The attention economy and the Net,” First Monday, vol. 2, no. 4, 1997, doi: 10.5210/fm.v2i4.519. DOI: https://doi.org/10.5210/fm.v2i4.519
V. R. Bhargava and M. Velasquez, “Ethics of the Attention Economy: The Problem of Social Media Addiction,” Business Ethics Quarterly, vol. 31, no. 3, pp. 321–359, 2021, doi: DOI: 10.1017/beq.2020.32. DOI: https://doi.org/10.1017/beq.2020.32
X. Xu, J. Wang, H. Peng, and R. Wu, “Prediction of academic performance associated with internet usage behaviors using machine learning algorithms,” Comput. Human Behav., vol. 98, pp. 166–173, 2019. DOI: https://doi.org/10.1016/j.chb.2019.04.015
A. López-Garcia, O. Blasco-Blasco, M. Liern-Garc’ia, and S. E. Parada-Rico, “Early detection of students’ failure using Machine Learning techniques,” Operations Research Perspectives, vol. 11, p. 100292, 2023. DOI: https://doi.org/10.1016/j.orp.2023.100292
M. Ramzan and others, “From Social Media Reactions to Grades: A Machine Learning-Based SocialNet Analysis for Academic Performance Prediction,” EAI Endorsed Transactions on AI and Robotics, 2025, doi: 10.4108/airo.8171. DOI: https://doi.org/10.4108/airo.8171
A. Al Mamun and others, “Impact of the Use of Social Media Among University Students Using Machine Learning,” in Communication and Intelligent Systems. ICCIS 2023. Lecture Notes in Networks and Systems, Springer, 2024. doi: 10.1007/978-981-97-2082-8_15. DOI: https://doi.org/10.1007/978-981-97-2082-8_15
R. Martinez and others, “Use of machine learning to measure the influence of behavioral and personality factors on academic performance,” IEEE Latin America Transactions, vol. 17, no. 3, 2019, doi: 10.1109/TLA.2019.8871822. DOI: https://doi.org/10.1109/TLA.2019.8891928
R. Martelo and others, “Incidencia de las redes sociales en el rendimiento académico de los estudiantes de la universidad,” Revista Espacios, vol. 38, no. 51, 2017.
L. Contreras, H. Fuentes, and J. Rodríguez, “Predicción del rendimiento académico como indicador de éxito/fracaso de los estudiantes de ingeniería, mediante aprendizaje automático,” Formación universitaria, vol. 13, no. 5, pp. 233–246, 2020, doi: 10.4067/S0718-50062020000500233. DOI: https://doi.org/10.4067/S0718-50062020000500233
P. Chapman et al., “CRISP-DM 1.0: Step-by-step data mining guide,” 2000.
M. S. Gordon and C. M. Ohannessian, “Social media use and academic achievement among early adolescents,” Youth Soc., 2024, doi: 10.1177/0044118X241234567.
A. D. Solano-barliza, “Enseñanza de la analítica de datos usando aprendizaje basado en proyectos colaborativos Teaching data analytics using collaborative project-based learning,” Formación Universitaria, vol. 16, no. 6, pp. 23–32, 2023. DOI: https://doi.org/10.4067/S0718-50062023000600023
Gil-Vera, Víctor D., & Quintero-López, Catalina. (2021). Predicción del rendimiento académico estudiantil con redes neuronales artificiales. Información tecnológica, 32(6), 221-228. https://dx.doi.org/10.4067/S0718-07642021000600221 DOI: https://doi.org/10.4067/S0718-07642021000600221
Hemal, S.H., Khan, M.A.R., Ahammad, I. et al. Predicting the impact of internet usage on students’ academic performance using machine learning techniques in Bangladesh perspective. Soc. Netw. Anal. Min. 14, 66 (2024). https://doi.org/10.1007/s13278-024-01234-9 DOI: https://doi.org/10.1007/s13278-024-01234-9
Bowers, A. J., & Zhou, X. (2019). Receiver Operating Characteristic (ROC) Area Under the Curve (AUC): A Diagnostic Measure for Evaluating the Accuracy of Predictors of Education Outcomes. Journal of Education for Students Placed at Risk (JESPAR), 24(1), 20–46. https://doi.org/10.1080/10824669.2018.1523734 DOI: https://doi.org/10.1080/10824669.2018.1523734
Barliza, A. S., Gómez, I. C., Caballero, J. M., & Muñoz, S. V. (2025). Towards a National Artificial Intelligence Policy in Colombia: A Comparative Analysis of International Frameworks. OnBoard Knowledge Journal, 1-13. DOI: https://doi.org/10.70554/OBJK2025.v01n01.02
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Andrés Solano-Barliza; Inés Figueroa-Sarmiento; Fabio Romero-Gómez
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The authors retain copyright and grant the journal the right to publish the work under a Creative Commons Attribution License, which allows third parties to use the published content as long as they credit the author(s) and the publication in OnBoard Knowledge Journal.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
a 