APPLICATION OF MACHINE LEARNING METHODS IN THE DEVELOPMENT OF DIGITAL DECISION SUPPORT SYSTEMS FOR SCHOOL LOCATION IN URBAN AREAS

Authors

A.A. Ivanov Kyrgyz-German Institute of Applied Informatics
A.A. Bakirov Kyrgyz-German Institute of Applied Informatics
A.T. Asanbekov Kyrgyz-German Institute of Applied Informatics
Yu.S. Koryakina Institute of Machine Science, Automation and Geomechanics of the National Academy of Sciences of the Kyrgyz Republic

Keywords:

machine learning, decision support system, urban data, school location, educational infrastructure, education management information system (EMIS), school capacity analysis, population density, digital map

Abstract

This article considers the development of a digital decision-support system for locating new schools in urban areas. Sources of open data on population and educational institutions, methods for analyzing population density and school utilization, and approaches to spatial data visualization on a map are considered. Existing methods for determining the need for educational infrastructure are analyzed. Based on this analysis, a model for identifying priority areas for new school construction using data analysis methods and elements of machine learning is proposed. The developed system can formulate recommendations on the location of educational institutions based on an analysis of the urban environment.

References

1. Конституция Кыргызской Республики (принята референдумом 11 апреля 2021 года). — Бишкек, 2021.

2. Национальный статистический комитет Кыргызской Республики. Официальный сайт https://stat.gov.kg/

3. Национальный статистический комитет Кыргызской Республики. Статистика населения: https://stat.gov.kg/ru/statistics/naselenie/

4. Информационная система управления образованием Кыргызской Республики (ИСУО). Статистические данные: https://1mektep.edu.gov.kg/ru/statistics

5. OpenStreetMap contributors. OpenStreetMap: свободная карта мира: https://www.openstreetmap.org/

6. UNESCO. OpenEMIS — Education Management Information System: https://www.openemis.org/ .

7. Pedregosa F., Varoquaux G., Gramfort A. et al. Scikit-learn: Machine Learning in Python // Journal of Machine Learning Research. — 2011. — Vol. 12. — P. 2825–2830.

8. Friedman J.H. Greedy Function Approximation: A Gradient Boosting Machine // Annals of Statistics. — 2001. — Vol. 29. — No. 5. — P. 1189–1232.

9. Goodfellow I., Bengio Y., Courville A. Deep Learning. — Cambridge: MIT Press, 2016.

10. Batty M. The New Science of Cities. — Cambridge: MIT Press, 2013.

11. Longley P.A., Goodchild M.F., Maguire D.J., Rhind D.W. Geographic Information Systems and Science. — Wiley, 2015.

12. United Nations. World Urbanization Prospects. — New York, 2018.

13. United Nations, Department of Economic and Social Affairs, Population Division. World Urbanization Prospects: The 2025 Revision. — New York: United Nations, 2025.

14. Li J., Wang Y. Characteristic Analysis and Integration Method of Urban Planning Data Based on GIS of Internet of Things // Sustainable Computing: Informatics and Systems. — 2022. — Vol. 36. — Article 100801.

15. Friedman J.H. Greedy Function Approximation: A Gradient Boosting Machine // Annals of Statistics. — 2001. — Vol. 29, No. 5. — P. 1189-1232.

16. Чирягов, А. К. Методологические основы построения устойчивых моделей машинного обучения с использованием вероятностно-статистических методов / А. К. Чирягов, С. В. Корякин, К. Р. Карабакиров // Проблемы автоматики и управления. – 2026. – № 1(55). – С. 152-161. – EDN QLHKUW.