Comparative Analysis of Forecasting Models for Student Enrollment in Kazakhstan's General Secondary Education System
DOI:
https://doi.org/10.31489/2025ec4/1200Keywords:
regional analysis, time series analysis, demographic growth, student enrollment forecasting, educational planningAbstract
We compared seven forecasting models to predict student enrollment in Kazakhstan's schools using data from 2020-2024. We tested cohort component models, cohort survival models, trend regression with demographic factors, linear trend models, exponential smoothing, multi-factor regression, and weighted moving averages across 20 regions (17 regions and 3 cities) with about 3.9 million students. We measured how accurate each model was using Mean Absolute Percentage Error (MAPE). We trained models on 2020-2023 data and tested them on 2024 numbers. The linear trend model worked best, with 0.70% MAPE nationally and 0.77% MAPE across regions. Demographic models didn't work as well—cohort models did poorly at the regional level even though they have good theory behind them. Our forecasts for 2025-2027 show national enrollment growing from 3.9 million to 4.2 million students, but growth varies a lot by region. Big cities like Astana will grow 24.05% and Almaty 12.81%, while some regions will barely grow at all. Our results help educational planners pick the right forecasting methods for different areas. This study fills a research gap for post-Soviet countries where detailed forecasting evaluations are hard to find.
References
Aji, B. W., Septiani, N. Z., Putri, W. M., Irawanto, B., Surarso, B., Farikhin, & Dasril, Y. (2023). Prediction of Indonesia school enrollment rate by using adaptive neuro fuzzy inference system. Indonesian Journal of Artificial Intelligence and Data Mining, 6(1), 40–46.
Aksenova, S. S., Zhang, D., & Lu, M. (2006). Enrollment prediction through data mining. In Proceedings of the 2006 International Conference on Data Mining (pp. 510–515). IEEE.
Bernhardt, V. L., Pullum, T. W., & Graham, S. N. (1983, April). Seattle's small-area approach to forecasting enrollments at the school level. Paper presented at the Annual Meeting of the American Educational Research Association, Montreal, Canada.
Braden, B., & Others. (1972). Enrollment forecasting handbook introducing confidence limit computations for a cohort-survival technique. New England School Development Council; Educational Facilities Laboratories, Inc.
Chen, C.-C., Chen, Y., & Kang, C.-Y. (2021). Estimating student-teacher ratio with ARIMA for primary education in fluctuating enrollment. ICIC Express Letters, Part B: Applications, 12(6), 515–523.
Chen, Q. (2022). A comparative study on the forecast models of the enrollment proportion of general education and vocational education. International Education Studies, 15(6), 109–126. https://doi.org/10.5539/ies.v15n6p109
Fabricant, R., & Weinman, J. (1972). Forecasting first grade public school enrollment by neighborhood. Demography, 9(4), 625–632.
GLA Intelligence. (2018). 2018 GLA school place demand projections. Greater London Authority.
Grip, R. S., & Grip, M. L. (2019). Using multiple methods to provide prediction bands of K-12 enrollment projections. Population Research and Policy Review, 38(5), 635–650. https://doi.org/10.1007/s11113-019-09533-2
Haynes, D. A. II. (2014). Improving enrollment projections through the application of geographic principles: Iowa 1999–2011 (Doctoral dissertation). University of Iowa.
Huynh Van, S., Nguyen Thi, H., Nguyen Vinh, K., Sam Vinh, L., & Giang Thien, V. (2019). Forecasting the results of students attending school in Vietnam by geographical area. International Journal of Education and Practice, 7(3), 274–285. https://doi.org/10.18488/journal.61.2019.73.274.285
Hussar, W. J., & Bailey, T. M. (2016). Projections of education statistics to 2024 (NCES 2016-013). U.S. Department of Education, National Center for Education Statistics.
James, F. (2021). Neural network-based time series forecasting of student enrollment with exponential smoothing baseline and statistical analysis of performance (Master’s report). Kansas State University.
Kornelio, S., Balan, R. T., & Deogratias, E. (2024). Forecasting students’ enrolment in Tanzania government primary schools from 2021 to 2035 using ARIMA model. International Journal of Curriculum and Instruction, 16(1), 162–174.
Langley, R. J. (1997). The use and development of geographical information systems (GIS) and spatial modelling for educational planning (Doctoral dissertation). University of Leeds.
Lavilles, R. Q., & Arcilla, M. J. B. (2012). Enrollment forecasting for school management system. International Journal of Modeling and Optimization, 2(5), 563–566.
Marinoiu, C. (2014). Modeling and forecasting the gross enrollment ratio in Romanian primary school. Annals of the Constantin Brâncuși University of Târgu Jiu, Economy Series, 3, 17–22.
Miller, M. A. (2008). Planning for enrollment growth using land use data to determine future school sites. Transportation Research Record, 2074(1), 12–20. https://doi.org/10.3141/2074-02
Pajankar, V. D., & Srivastava, S. (2019). An approach of estimating school enrolment with reconstructive cohort approach. Journal of Physics: Conference Series, 1366, 012116. https://doi.org/10.1088/1742-6596/1366/1/012116
Pedamallu, C. S., Ozdamar, L., Ganesh, L. S., Weber, G.-W., & Kropat, E. (2010). A system dynamics model for improving primary education enrollment in a developing country. Organizacija, 43(3), 90–100. https://doi.org/10.2478/v10051-010-0010-5
Proehl, R. S. (2000). Enrollment forecast for Horizon Christian School 2005–2015. Population Research Center, Portland State University. https://pdxscholar.library.pdx.edu/enrollmentforecasts/71
Rynerson, C., & Ollinger, J. (2018). Portland Public Schools enrollment forecasts 2018–19 to 2032–33. Population Research Center, Portland State University. https://pdxscholar.library.pdx.edu/enrollmentforecasts/123
Rynerson, C., & Wei, C. (2021). Centennial School District enrollment forecasts 2021–22 to 2030–31. Population Research Center, Portland State University. https://pdxscholar.library.pdx.edu/enrollmentforecasts/148
Rynerson, C., & Wei, C. (2022). Salem-Keizer Public Schools enrollment forecast 2022–23 to 2041–42. Population Research Center, Portland State University. https://pdxscholar.library.pdx.edu/enrollmentforecasts/139
Sahane, M., Sirsat, S., Khan, R., & Aglave, B. (2014). Prediction of primary pupil enrollment in government school using data mining forecasting technique. International Journal of Advanced Research in Computer Science and Software Engineering, 4(9), 656–661.
Shafii, N. H., Alias, R., Shamsudin, S. R., & Nasir, D. S. M. (2021). Fuzzy time series for projecting school enrolment in Malaysia. Journal of Computing Research and Innovation, 6(1), 11–21. https://doi.org/10.24191/jcrinn.v6i1.180
Stronge, W. B., & Schultz, R. R. (1981). Models for projecting school enrollment. Educational Evaluation and Policy Analysis, 3(5), 75–81.
Sweeney, S. H., & Middleton, E. J. (2005). Multiregional cohort enrollment projections: Matching methods to enrollment policies. Population, Space and Place, 11(5), 361–379. https://doi.org/10.1002/psp.379
Tang, H.-W. V., & Yin, M.-S. (2012). Forecasting performance of grey prediction for education expenditure and school enrollment. Economics of Education Review, 31(4), 452–462. https://doi.org/10.1016/j.econedurev.2011.12.007
Wang, Q., Wang, Y., & Wang, G. (2023). Research on space potential excavating of existing primary school under the base of schooling demand forecasting model: A case study in new urban districts. Ain Shams Engineering Journal, 14, 101871. https://doi.org/10.1016/j.asej.2022.101871
Yan, B. (2024). Dynamic analysis of influencing factors and forecast of development trend of “disappearance of rural primary schools.” Journal of Service Science and Management, 17(1), 75–88. https://doi.org/10.4236/jssm.2024.171003
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 BUKETOV BUSINESS REVIEW
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
