.png)
Data-Driven Forecasting of Special Education Enrollment: An Explainable Machine Learning Approach
Abstract
The application of machine learning algorithms in the field of special education remains incipient despite advances achieved in other sectors. This field faces challenges related to inclusion, planning, and resource allocation, especially in contexts where administrative records are often underutilized for analytical purposes. This study proposes an explainable forecasting approach based on 23,905 historical data records to anticipate educational demand in the Special Basic Education (SBE) modality, aiming to develop and validate a Random Forest model applied to a multivariate database of official enrollment records from 2019 to 2024, projecting a slight global contraction from 28,000 to 26,800 enrollments by 2025. The findings reveal nonlinear growth patterns differentiated by region and educational level, mainly in Early SBE (ages 0 to 2), Preschool, and Primary, with a general trend of increasing demand in coastal and highland regions. The models achieved high levels of accuracy (R² > 0.97), with a Root Mean Squared Error (RMSE) below 190, a Mean Absolute Error (MAE) under 70, and a Mean Absolute Percentage Error (MAPE) below 10%. These results demonstrate the model’s utility as a strategic decision-support tool by optimizing resource planning in an education system characterized by territorial heterogeneity. The novelty of this study lies in integrating geospatial analysis and predictive algorithmic interpretability within an explainable artificial intelligence framework, fostering more equitable, transparent, and evidence-based educational planning.
Keywords
Full Text:
PDFReferences
UNESCO, Inclusion and education: All means all. Global Education Monitoring Report 2020. Paris: UNESCO, 2020. [Online]. Available: https://unesdoc.unesco.org/ark:/48223/pf0000373718
W. J. Blanchett, J. K. Klingner, and B. Harry, “The intersection of race, culture, and disability: Implications for urban education,” Urban Education, vol. 44, no. 4, pp. 389–409, 2009. [Online]. Available: https://doi.org/10.1177/0042085909338686
B. Harry and J. K. Klingner, Why are so many minority students in special education? Understanding race and disability in schools. New York: Teachers College Press, 2014. [Online]. Available: https://books.google.es/books?id=4b2_AwAAQBAJ
T. A. Fiore, L. M. Harwell, J. Blackorby, and K. S. Finnigan, Charter schools and students with disabilities: A national study. Final report (ED452657). Washington, DC: U.S. Dept. of Education, 2000. [Online]. Available: https://eric.ed.gov/?id=ED452657
P. Lipman, The new political economy of urban education: Neoliberalism, race, and the right to the city. New York: Routledge, 2011. [Online]. Available: https://core.ac.uk/download/pdf/236135746.pdf
Ministerio de Educación del Perú, Censo Educativo 2018: Informe nacional. Lima: Oficina de Medición de la Calidad de los Aprendizajes, 2018.
C. Nelson, P. Berman, R. Perry, and D. Silverman, The state of charter schools 2000: Fourth-year report. Washington, DC: U.S. Dept. of Education, 2000. [Online]. Available: https://books.google.com.pe/books?id=fgrltWLdPXYC
G. Stock and M. Schultz, “Medicaid expansions and special education enrollments: Evidence from administrative panel data,” Journal of Policy Analysis and Management, vol. 44, no. 1, pp. 22–41, 2025. [Online]. Available: https://doi.org/10.1002/pam.22471
J. Senese and M. A. Winters, “La elección de escuela y los estudiantes con discapacidad: Evidencia de datos administrativos,” Remedial and Special Education, vol. 46, no. 2, 2024. [Online]. Available: https://doi.org/10.1177/07419325241262699
Ministerio de Educación del Perú, Estadísticas de matrícula en Educación Básica Especial. Lima: Dirección de Educación Básica Especial, 2022.
C. Romero and S. Ventura, “Educational data mining and learning analytics: An updated survey [Preprint],” arXiv, 2024. [Online]. Available: https://arxiv.org/abs/2402.07956
W. Rojas Paucar, A. O. Carranza López, E. M. Chávez Garcés, and E. L. Medina Soto, “Patrones oncológicos en el Sistema Integral de Salud de Perú: Ciencia de Datos con K-Medias,” Revista Cubana de Investigaciones Biomédicas, vol. 44, Art. 3777, 2025. [Online]. Available: https://revibiomedica.sld.cu/index.php/ibi/article/view/3777
A. A. Shafi, R. Little, and S. Case, “Children’s education in secure custodial settings: Towards a global understanding of effective policy and practice,” International Journal of Educational Development, vol. 82, p. 102379, 2021. [Online]. Available: https://doi.org/10.1016/j.ijedudev.2021.102379
L. Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. [Online]. Available: https://doi.org/10.1023/A:1010933404324
C. Molnar, Interpretable machine learning: A guide for making black box models explainable, 2nd ed. Leanpub, 2022. [Online]. Available: https://christophm.github.io/interpretable-ml-book/
K. Razzaq and M. Shah, “Advancing cybersecurity through machine learning: A scientometric analysis of global research trends and influential contributions,” Journal of Cybersecurity and Privacy, vol. 5, no. 2, p. 12, 2025. [Online]. Available: https://www.mdpi.com/2624-800X/5/2/12
M. D. Ganggayah, M. Y. Loh, R. Y. Yap, C. F. Chew, T. L. Tay, and K. F. Wong, “Accelerating autism spectrum disorder care: A rapid review of data science applications in diagnosis and intervention,” Asian Journal of Psychiatry, vol. 108, p. 104498, 2025. [Online]. Available: https://doi.org/10.1016/j.ajp.2025.104498
M. D. Broda, M. Bogenschutz, P. Dinora, S. M. Prohn, S. Lineberry, and E. Ross, “Using machine learning to predict patterns of employment and day program participation,” American Journal on Intellectual and Developmental Disabilities, vol. 126, no. 6, pp. 477–491, 2021. [Online]. Available: https://doi.org/10.1352/1944-7558-126.6.477
N. Wankhede, M. Kale, M. Shukla, D. Nathiya, R. Roopashree, P. Kaur, B. Goyanka, S. Rahangdale, B. Taksande, A. Upaganlawar, M. Khalid, S. Chigurupati, M. Umekar, S. R. Kopalli, and S. Koppula, “Leveraging AI for the diagnosis and treatment of autism spectrum disorder: Current trends and future prospects,” Asian Journal of Psychiatry, vol. 101, p. 104241, 2024. [Online]. Available: https://doi.org/10.1016/j.ajp.2024.104241
L. Ghunaim, Y. Al-Shamma, H. Al-Ramahi, and O. Al-Qawasmi, “The Future of Pediatric Care: AI and ML as Catalysts for Change in Genetic Syndrome Management,” Jordan Medical Journal, vol. 58, no. 4, pp. 510–528, 2024. [Online]. Available: https://doi.org/10.35516/jmj.v58i4.2787
A. S. C. Tan, F. Ali, and K. K. Poon, “Bienestar subjetivo de niños con necesidades educativas especiales: Predictores longitudinales mediante aprendizaje automático,” Applied Psychology: Health and Well-Being, vol. 17, no. 1, p. e12625, 2024. [Online]. Available: https://doi.org/10.1111/aphw.12625
A. Alkan, “The role of artificial intelligence in the education of students with special needs,” International Journal of Technology in Education and Science, vol. 8, no. 4, pp. 542–557, 2024. [Online]. Available: https://doi.org/10.46328/ijtes.569
U.S. Government Accountability Office (GAO), Charter schools: Additional federal attention needed to help protect access for students with disabilities. Washington, DC: GAO, 2012. [Online]. Available: https://www.gao.gov/products/gao-12-543
F. R. Waitoller, D. M. Maggin, and A. Trzaska, “A longitudinal comparison of enrollment patterns of students receiving special education in urban neighborhood and charter schools,” Journal of Disability Policy Studies, vol. 28, no. 1, pp. 3–12, 2017. [Online]. Available: https://doi.org/10.1177/1044207317694846
H. Shao, J. Peng, and X. Liu, “Course enrollment prediction using machine learning: A case study,” Education and Information Technologies, vol. 27, no. 4, pp. 5257–5277, 2022. [Online]. Available: https://doi.org/10.1007/s10639-021-10852-0
J. Chen, Y. Wang, and L. Zhou, “Time series classification with a multiscale convolutional neural network and attention mechanism,” Neural Computing and Applications, vol. 33, pp. 7445–7461, 2021. [Online]. Available: https://doi.org/10.1007/s00521-020-05634-z
K. K. Adusei, “Modeling of municipal waste disposal behaviors related to meteorological and astronomical seasons using recurrent neural network models [Master’s thesis],” The University of Regina (Canada), 2022. [Online]. Available: https://www.proquest.com/openview/43375cf41062a40a8ab63a5fb34ad4eb/1?pq-origsite=gscholar&cbl=18750&diss=y
P. Bhoj, A. Sharma, and M. P. S. Bhatia, “A hybrid deep learning model for forecasting residential energy consumption,” Applied Energy, vol. 308, p. 118357, 2022. [Online]. Available: https://doi.org/10.1016/j.apenergy.2021.118357
R. Tapio and D. Tarepe, “Comparative analysis of Random Forest and hybrid ARIMA Random Forest models for student enrollment forecasting in higher education,” Journal of Advances in Mathematics and Computer Science, vol. 40, no. 3, pp. 124–136, 2025. [Online]. Available: https://doi.org/10.9734/jamcs/2025/v40i31982
DOI: https://doi.org/10.47738/jads.v7i1.1046
Refbacks
- There are currently no refbacks.
Journal of Applied Data Sciences
| ISSN | : | 2723-6471 (Online) |
| Publisher | : | Bright Publisher |
| Website | : | http://bright-journal.org/JADS |
| : | taqwa@amikompurwokerto.ac.id (principal contact) | |
| support@bright-journal.org (technical issues) |
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0