Forecasting student demand using regression models: a comparative study of the academic unit of engineering, industry and construction of the Catholic University of Cuenca
Keywords:
demand forecasting, data augmentation, neutrosophic AHP, TOPSIS, university managementAbstract
Introduction: This study develops a methodology for forecasting student demand at the Academic Unit of Engineering, Industry, and Construction of the Catholic University of Cuenca, addressing the challenge of short time series. Materials and methods: Daily enrollment data (22 observations/program) were used. To overcome data scarcity, data augmentation was applied by combining SMOTE interpolation with bootstrapping, expanding the sample. Four regression models were evaluated on this augmented data: linear, polynomial (2nd and 3rd degree), and logistic. The selection of the optimal model for each of the five programs was performed using a multi-criteria framework that integrates the Neutrosophical Analytic Hierarchy Process (AHP)—to weight criteria such as R², RMSE, MAPE, and MAE under uncertainty—and the TOPSIS technique for the final ranking. Results: The data augmentation allowed the series to be expanded to approximately 55 observations. The TOPSIS analysis revealed that there was no single optimal model: the third-degree polynomial model was selected for Civil and Industrial Engineering; the second-degree model for Architecture and Electrical Engineering; and the linear model for Design. Discussion: The proposed methodology proves superior to the use of deep learning with limited data, avoiding overfitting. The combination of data augmentation and neutrosophic multi-criteria selection provides a robust, transparent, and adaptable framework that manages uncertainty and justifies model selection based on the specific dynamics of each program. Conclusions: This study validates that data augmentation and model selection using Neutrosophic AHP-TOPSIS constitute an effective and pedagogical tool for demand forecasting in data-constrained contexts, offering university management a tool for more precise and evidence-based academic and resource planning.
References
Abdel-Basset, M., Mohamed, M., & Smarandache, F. (2018). A hybrid neutrosophic group ANP-TOPSIS framework for supplier selection problems. Symmetry, 10(6), 226. https://doi.org/10.3390/sym10060226
Barzola-Monteses, J., Rodríguez-Cedeño, J., & Smarandache, F. (2024). Detection of cardiovascular diseases using predictive models based on deep learning techniques: A hybrid neutrosophic AHP-TOPSIS approach for model selection. Neutrosophic Sets and Systems, 66, 135–147.
Bergmeir, C., Hyndman, R. J., & Benítez, J. M. (2016). Bagging exponential smoothing methods using STL decomposition and bootstrapping. International Journal of Forecasting, 32(2), 303–312. https://doi.org/10.1016/j.ijforecast.2015.09.005
Castañeda Sánchez, W. A., Polo Escobar, B. R., & Vega Huincho, F. (2023). Redes neuronales artificiales: una medición de aprendizajes de pronósticos como demanda potencial. Universidad, Ciencia y Tecnología, 27(118), 51–60.
Cerqueira, V., Torgo, L., & Soares, C. (2024). Time series data augmentation as an imbalanced learning problem. arXiv preprint arXiv:2404.18537.
Diponegoro, M. H., Kusumawardani, S. S., & Hidayah, I. (2021). Tinjauan pustaka sistematis: Implementasi metode deep learning pada prediksi kinerja murid. Jurnal Nasional Teknik Elektro Dan Teknologi Informasi, 10(2), 131–138. https://doi.org/10.22146/jnteti.v10i2.1417
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
Gulum, P., Gökkuş, Ü., & Gökkuş, A. (2021). A two level interval valued neutrosophic AHP integrated TOPSIS for post-earthquake fire risk assessment. Journal of Intelligent & Fuzzy Systems, 41(1), 1599–1612. https://doi.org/10.3233/JIFS-210701
Hwang, C. L., & Yoon, K. (1981). Multiple attribute decision making: Methods and applications. Springer-Verlag.
Iwana, B. K., & Uchida, S. (2021). An empirical survey of data augmentation for time series classification with neural networks. PLoS ONE, 16(7), e0254841. https://doi.org/10.1371/journal.pone.0254841
Jiang, W., Ling, L., Zhang, D., Lin, R., & Zeng, L. (2023). A time series forecasting model selection framework using CNN and data augmentation for small sample data. Neural Processing Letters, 55, 3357–3386. https://doi.org/10.1007/s11063-022-11113-z
Liu, Q., Shakya, R., Jovanovic, J., Khalil, M., & Gašević, D. (2025). Ensuring privacy through synthetic data generation in education. British Journal of Educational Technology, 56(2), 445–462. https://doi.org/10.1111/bjet.13576
Morales Echeverria, D. A., & Galarza Arrieta, S. del R. (2024). Acceso a la educación superior pública en Ecuador y limitación de cupos como vulneración de derechos. Revista de Investigación Educativa Niveles, 1(2), 5–13. https://doi.org/10.61347/rien.v1i2.60
Popovic, N. (2023). How to improve the accuracy of your time series forecast by using bootstrapping. Medium. https://medium.com/@NiclasPopovic0402/how-to-improve-the-accuracy-of-your-time-series-forecast-by-using-bootstrapping-c5a81ce3abe6
Qu, H., Wang, Z., & Li, Y. (2024). A time series data augmentation method based on SMOTE. En 2024 5th International Conference on Computer Vision, Image and Deep Learning (CVIDL) (pp. 114–118). IEEE. https://doi.org/10.1109/CVIDL61864.2024.10587816
Rachel, J., Jeyakarthi, J., & Mary, S. A. (2024). Enhancing biometric system selection: A hybrid AHP-neutrosophic soft set fuzzy TOPSIS approach. BMC Research Notes, 17(1), 246. https://doi.org/10.1186/s13104-024-06903-8
Rodríguez Morachis, M. A., Terrazas Mata, L. E., & Zorrilla Briones, F. (2024). Estimación de demanda estudiantil en una institución educativa para calcular capacidad docente y aulas utilizando modelo de pronósticos. RIDE Revista Iberoamericana Para La Investigación y El Desarrollo Educativo, 14(28). https://doi.org/10.23913/ride.v14i28.1790
Semenoglou, A. A., Spiliotis, E., & Assimakopoulos, V. (2023). Data augmentation for univariate time series forecasting with neural networks. Pattern Recognition, 135, 109–127. https://doi.org/10.1016/j.patcog.2022.109127
Sepúlveda, G. (2021). Pronóstico para la demanda de inscritos en estudios de educación superior a nivel pregrado en la Universidad de la Amazonia [Tesis de grado, Universidad de la Amazonia].
Shao, L., Vannan, S. K., & Kaur, H. (2021). Machine learning methods for course enrollment prediction. IEEE Transactions on Education, 64(3), 234–243. https://doi.org/10.1109/TE.2021.3058234
Smarandache, F., Vázquez, M. Y. L., Cevallos-Torres, L., & Barco, L. J. L. (2025). Neutrosofía: Orígenes, aplicaciones y perspectivas en la lógica contemporánea. Neutrosophic Computing and Machine Learning, 37, 1–10.
Syamsudin, A., & Maarif, M. S. (2024). A comparative study of Lagrange and Gregory forward interpolation techniques for estimating new student enrollment trends in Faculty of Tarbiyah at IAIN Kediri. Journal Focus Action of Research Mathematic, 7(1), 173–189. https://doi.org/10.30762/f_m.v7i1.3179
Triambak, S., Mahapatra, D. P., Mallick, N., & Sahoo, R. (2021). A new logistic growth model applied to COVID-19 fatality data. Epidemics, 37, 100515. https://doi.org/10.1016/j.epidem.2021.100515
Universidad Católica de Cuenca. (2025). Modelo educativo. https://www.ucacue.edu.ec/
Zhan, C., Deho, O. B., Zhang, X., Joksimovic, S., & Gašević, D. (2023). Synthetic data generator for student data serving learning analytics: A comparative study. Learning Letters, 1(1), 1–11.
Zhou, Y., Johansen, B., & Tian, Y. (2023). Improving time series forecasting with Mixup data augmentation. En Amazon Science Conference (pp. 1–8).
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Jorge Leopoldo Pauta Riera, Maikel Yelandi Leyva Vazquez, Dayron Rumbaut Rangel
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
This journal provides immediate open access to its content, based on the principle that offering the public free access to research helps a greater global exchange of knowledge. Each author is responsible for the content of each of their articles.
Universidad de Oriente 