Optimizing School Resource Allocation in Lima Puluh Kota Regency through Random Forest Classification of Clustered Student Enrollment Trends

DOI

10.2991/978-94-6239-636-4_17How to use a DOI?

Keywords

Clustering; Classification; Student Population; School Change Patterns; K-Means; Random Forest

Abstract

The pattern of changes in student numbers in public elementary schools is a strategic issue that affects the effective distribution of educational resources, particularly in Lima Puluh Kota Regency. Imbalances in student growth or decline across schools can impact the need for teaching staff, classroom space, and budget allocation. This study aims to classify public elementary schools based on patterns of student number changes, as an effort to support data-driven education policy planning on 359 public elementary schools with student number data from year 2020-2024, as well as supporting attributes. The method used in this study is K-Means clustering and Random Forest classification. Clustering resulted in four clusters: increasing, stable, moderately decreasing, and sharply decreasing student numbers. The classification models were evaluated using K-Fold Cross-Validation with accuracy, precision, recall, and F1-score metrics. The results showed that the pure student-based classification produced an average accuracy of 91.9%, while the trend-based model had an accuracy of 39%. Although trend-based model currently had a lower accuracy, its clustering results were considered more relevant for long-term policy because they were able to illustrate the direction of student change. Descriptive analysis of each cluster also showed a link between the decline in student numbers and low school resource allocation. These findings can be used to support a more targeted and adaptive distribution of educational resources.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Lestari Margatama
AU  - Yopie Hidayat
AU  - Indra Riyanto
PY  - 2026
DA  - 2026/04/28
TI  - Optimizing School Resource Allocation in Lima Puluh Kota Regency through Random Forest Classification of Clustered Student Enrollment Trends
BT  - Proceedings of the International Conference on Cross- Disciplinary Academic Research 2025 - Track 1 Advances in Computing, Electronics, Engineering, and Mathematics (ICAR-T1 2025)
PB  - Atlantis Press
SP  - 215
EP  - 225
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-636-4_17
DO  - 10.2991/978-94-6239-636-4_17
ID  - Margatama2026
ER  -