Modelos predictivos multidimensionales del rendimiento académico basados en variables académicas, conductuales y de interacción digital en estudiantes universitarios

Roberto Vinicio Defas Ayala; Juan Andrés Romero Torres; Roberto Fernando Lozada Lozada

doi:10.65598/rps.6164

Autores/as

Roberto Vinicio Defas Ayala Universidad Central del Ecuador, Ecuador https://orcid.org/0009-0002-3240-3595
Juan Andrés Romero Torres Universidad de las Fuerzas Armadas ESPE, Ecuador https://orcid.org/0009-0001-8570-5098
Roberto Fernando Lozada Lozada Universidad Politécnica Salesiana, Ecuador https://orcid.org/0009-0007-4634-7981

DOI:

https://doi.org/10.65598/rps.6164

Palabras clave:

Rendimiento académico, Modelos predictivos, Learning analytics, Educación superior, Machine learning, Interacción digital

Resumen

El rendimiento académico en educación superior constituye un indicador clave de calidad y permanencia estudiantil, particularmente en contextos mediados por tecnologías digitales, el objetivo de este estudio fue analizar sistemáticamente la evidencia científica reciente sobre modelos predictivos multidimensionales del rendimiento académico basados en variables académicas, conductuales y de interacción digital en estudiantes universitarios. Se realizó una revisión sistemática conforme a las directrices PRISMA, consultando bases de datos indexadas entre 2020 y 2025, y seleccionando 23 estudios empíricos que emplearon técnicas de minería de datos, modelos de ensemble, redes neuronales profundas y enfoques de inteligencia artificial explicable. Los resultados evidencian que los modelos que integran simultáneamente dimensiones académicas, conductuales y digitales presentan mayor precisión predictiva frente a enfoques unidimensionales, asimismo, aunque los métodos de ensemble y las arquitecturas profundas muestran alto desempeño estadístico, persisten desafíos relacionados con la interpretabilidad, la validación externa y la aplicabilidad institucional. A partir de la síntesis de la evidencia se propone un modelo conceptual estructural que articula estas tres dimensiones como base para sistemas de alerta temprana sostenible; se concluye que el avance del campo depende del equilibrio entre integración multidimensional, transparencia analítica y gobernanza ética de datos en educación superior.

Descargas

Los datos de descargas todavía no están disponibles.

Citas

Abdulkareem Shafiq, D., Marjani, M., Ahamed Ariyaluran Habeeb, R., & Asirvatham, D. (2025). Digital footprints of academic success: An empirical analysis of Moodle logs and traditional factors for student performance. Education Sciences, 15(3), 304. https://doi.org/10.3390/educsci15030304

Ahmed, W., Wani, M. A., Plawiak, P., Meshoul, S., Mahmoud, A., & Hammad, M. (2025). Machine learning-based academic performance prediction with explainability for enhanced decision-making in educational institutions. Scientific Reports, 15, 26879. https://doi.org/10.1038/s41598-025-12353-4

Alamri, R., & Alharbi, B. (2021). Explainable student performance prediction models: A systematic review. IEEE Access, 9, 33132–33143. https://doi.org/10.1109/ACCESS.2021.3061368

Almalawi, A., Soh, B., Li, A., & Samra, H. (2024). Predictive models for educational purposes: A systematic review. Big Data and Cognitive Computing, 8(12), 187. https://doi.org/10.3390/bdcc8120187

Bañeres, D., Rodríguez-González, M. E., Guerrero-Roldán, A. E., & Cortadas-Guasch, P. (2023). An early warning system to identify and intervene online dropout learners: A learning analytics approach. International Journal of Educational Technology in Higher Education, 20, 3. https://doi.org/10.1186/s41239-022-00371-5

Bravo-Agapito, J., Romero, S. J., & Pamplona, S. (2021). Early prediction of undergraduate student’s academic performance in completely online learning: A five-year study. Computers in Human Behavior, 115, 106595. https://doi.org/10.1016/j.chb.2020.106595

Chang, Y.-H., Chen, F.-C., & Lee, C.-I. (2025). Developing an early warning system with personalized interventions to enhance academic outcomes for at-risk students in Taiwanese higher education. Education Sciences, 15(10), 1321. https://doi.org/10.3390/educsci15101321

Chen, H.-C., Prasetyo, E., Tseng, S.-S., Putra, K. T., Prayitno, Kusumawardani, S. S., & Weng, C.-E. (2022). Week-wise student performance early prediction in virtual learning environment using a deep explainable artificial intelligence. Applied Sciences, 12(4), 1885. https://doi.org/10.3390/app12041885

Chen, X., Feng, S., Yin, K., Luo, J., & Chen, Y. (2023). A novel prediction model of students’ performance based on self-attention mechanism. Knowledge and Information Systems, 65, 733–758. https://doi.org/10.1007/s10115-022-01774-6

Christou, C., Mavrikis, M., & Holmes, W. (2023). Predicting student performance: A machine learning approach based on students’ learning behaviour. Education and Information Technologies, 28(9), 11563–11590. https://doi.org/10.1007/s10639-023-11738-5

Gaftandzhieva, S., Doneva, R., & Dochev, D. (2022). Exploring online activities to predict the final grade of student. Education and Information Technologies, 27(8), 11935–11958. https://doi.org/10.1007/s10639-021-10872-2

González Olivares, Á. L., de Juanas Oliva, Á., & Magro Gutiérrez, M. (2022). Educación inclusiva: Un modelo sostenible para la sociedad del siglo XXI. Revista Prisma Social, (37). https://revistaprismasocial.es/ps/article/view/4774

Liu, H., Singh, V. K., Choi, I., & Klein, P. (2022). A method for prediction and analysis of student performance that combines multi-dimensional features of time and space. Expert Systems with Applications, 205, 117658. https://doi.org/10.1016/j.eswa.2022.117658

Mejía Corredor, C., Said-Hung, E., & Gómez Ardila, S. E. (2023). La investigación en educación: Innovación pedagógica y educación virtual. Revista Prisma Social, (41). Recuperado a partir de https://revistaprismasocial.es/ps/article/view/5113

Romero Oliva, M. F., & Heredia Ponce, H. (2024). Formación inicial de la Docencia y Educación Lingüística: Factores de cambio social en el Horizonte 2030. Revista Prisma Social, (45), 1–3. Recuperado a partir de https://revistaprismasocial.es/ps/article/view/5480

Rojas, R., & Jiménez, J. (2024). A multidimensional model for early prediction of academic performance in online learning environments. IEEE Access, 12, 10784–10799. https://doi.org/10.1109/ACCESS.2024.3356846

Sahlaoui, H., Chaabane, F., & Ben Ammar, M. (2021). Predicting and interpreting student performance using ensemble models and Shapley additive explanations. Computers & Education: Artificial Intelligence, 2, 100036. https://doi.org/10.1016/j.caeai.2021.100036

Santos, O. C., Boticario, J. G., & Rodríguez, A. (2023). Early warning systems in higher education: A multidimensional learning analytics framework for student success. Computers & Education, 198, 104753. https://doi.org/10.1016/j.compedu.2023.104753

Shou, H., Xu, L., Li, P., & Shi, S. (2024). Student performance prediction from multi-source features in higher education: A machine learning approach. Applied Sciences, 14(6), 2522. https://doi.org/10.3390/app14062522

Wang, S., & Luo, B. (2024). Academic achievement prediction in higher education through interpretable modeling. PLOS ONE, 19(9), e0309838. https://doi.org/10.1371/journal.pone.0309838

Wang, X., Zhao, Y., Li, C., & Ren, P. (2023). ProbSAP: A comprehensive and high-performance system for student academic performance prediction. Pattern Recognition, 137, 109309. https://doi.org/10.1016/j.patcog.2023.109309

Wen, X., & Juan, H. (2023). Early prediction of students’ performance using a deep neural network based on online learning activity sequence. Applied Sciences, 13(15), 8933. https://doi.org/10.3390/app13158933

Zou, Y., Li, Z., Wang, J., & Chen, L. (2025). An interpretable machine learning framework for predicting academic performance in online higher education. Applied Sciences, 15(7), 3550. https://doi.org/10.3390/app15073550