A Cluster-based Framework for Enrollment Forecasting in Brazilian Schools
DOI:
https://doi.org/10.5753/reic.2026.8468Keywords:
Enrollment Forecasting, Bipartite Graphs, Clustering, Algorithmic Invisibility, PNLD, Context-Aware ModelingAbstract
Forecasting enrollments for policies such as the Brazilian National Textbook Program (PNLD) is hindered by traditional global predictive models that ignore school heterogeneity and often produce algorithmic invisibility in vulnerable contexts. The study proposes a Context-Aware Forecasting Framework based on split modeling strategies, using Direct Bipartite Graphs and Clustering Techniques. Experimental results show that context-specific feature engineering enables drastic dimensionality reduction—compressing 20 features within "Cluster 1" into a single PCA signal and reducing "Cluster 2" to 20 relevant attributes, representing a 94% dimensionality reduction in 81.25% of the tuples — while maintaining comparable predictive performance.
Downloads
Referências
Abideen, Z. u. et al. (2023). Analysis of enrollment criteria in secondary schools using machine learning and data mining approach. Electronics, 12(3):694. DOI: 10.3390/electronics12030694.
Asratian, A. S., Denley, T. M. J., and Häggkvist, R. (1998). Bipartite Graphs and Their Applications. Cambridge University Press.
Baker, R. S. (2019). Challenges for the future of educational data mining: The baker learning analytics prizes. Journal of Educational Data Mining, 11(1):1–17.
Correia, D. V. L. et al. (2025). Uncovering contextual clusters in brazilian public education. In Proceedings of the 18th Annual International Conference of Education, Research and Innovation (ICERI 2025).
Freeman, L. C. (1978). Centrality in social networks: Conceptual clarification. Social Networks, 1(3):215–239. DOI: 10.1016/0378-8733(78)90021-7.
Hamming, R. W. (1950). Error detecting and error correcting codes. The Bell System Technical Journal, 29(2):147–160. DOI: 10.1002/j.1538-7305.1950.tb00463.x.
Hotelling, H. (1933). Analysis of a complex of statistical variables into principal components. Journal of Educational Psychology, 24(6):417–441.
Hwang, S., Lee, Y., Jeon, B.-K., and Oh, S. H. (2025). Sales forecasting for new products using homogeneity-based clustering and ensemble method. Electronics, 14(3):520. DOI: 10.3390/electronics14030520.
Laurinec, P. and Lucka, M. (2018). Clustering-based forecasting method for individual consumers electricity load using time series representations. Open Computer Science, 8(1):38–50. DOI: 10.1515/comp-2018-0006.
Maia, J. et al. (2021). Assessing the educational performance of different brazilian school cycles using data science methods. PLOS ONE, 16(3):1–14. DOI: 10.1371/journal.pone.0248525.
Phakathi, E. N. (2015). The management of learning and teaching support materials in public schools: a comparative study. Master’s thesis, University of KwaZulu-Natal, Edgewood, South Africa.
Silva, L., de Cabral, L., Santos Júnior, J., Santos, L., Oliveira, T., Costa, B., Lobo, J., Pinho Júnior, D., Cruz, N., de Silva, R., and Pimentel, B. (2025a). Forecasting student enrollments in brazilian schools for equitable and efficient education resource allocation. Conference on Digital Government Research, 26. DOI: 10.59490/dgo.2025.939.
Silva, L. et al. (2025b). A computational approach to feature selection and enrollment forecasting in brazilian schools. Proceedings of the 11th International Conference on Artificial Intelligence and Applications. DOI: 10.5121/csit.2025.151910.
Spearman, C. (1904). The proof and measurement of association between two things. The American Journal of Psychology, 15(1):72–101.
Yang, S. et al. (2020). Student enrollment and teacher statistics forecasting based on time-series analysis. Computational Intelligence and Neuroscience, 2020:1246920. DOI: 10.1155/2020/1246920.
Zambon, L. and Terrazzan, E. A. (2013). Policies of didactic material in brazil: Organization of procedures for selection of textbooks in basic education public schools. Revista Brasileira de Estudos Pedagógicos, 94(237):585–602.
Zipf, G. K. (1949). Human behavior and the principle of least effort: An introduction to human ecology.
Downloads
Published
Como Citar
Issue
Section
Licença
Copyright (c) 2026 Os autores
Este trabalho está licenciado sob uma licença Creative Commons Attribution 4.0 International License.
