K-Means Clustering for Grouping Elementary School Facilities and Infrastructure in Indonesia

OK Muhammad Zikri Fadillah; Abdul Halim Hasugian

doi:10.36080/idealis.v9i2.3827

Authors

OK Muhammad Zikri Fadillah Ilmu Komputer, Sains Dan Teknologi, Universitas Islam Negeri Sumatera Utara, Medan, Indonesia
Abdul Halim Hasugian Ilmu Komputer, Sains Dan Teknologi, Universitas Islam Negeri Sumatera Utara, Medan, Indonesia

DOI:

https://doi.org/10.36080/idealis.v9i2.3827

Keywords:

Davies-Bouldin Index, Klasterisasi K-Means, Indeks Davies-Bouldin, Infrastruktur Pendidikan, Sekolah dasar, Pemetaan Infrastruktur, Educational Infrastructure, Elementary School, Infrastructure Mapping, K-Means Clustering

Abstract

Equitable access to quality basic education remains a national priority in Indonesia, yet the condition of elementary school facilities and infrastructure still varies considerably across regions. This research applies the K-Means Clustering algorithm to classify the condition of elementary school facilities and infrastructure at the regency/city level in Indonesia, addressing disparities in basic education facilities through a more objective, data-based mapping approach. Data were obtained from the 2025 Data Portal of the Ministry of Primary and Secondary Education, covering 514 regencies/cities and six indicators: classrooms, libraries, laboratories, school health units, boys’ toilets, and girls’ toilets. Each indicator was converted into a numerical score based on four condition categories and normalized using Min-Max Normalization prior to clustering. The number of clusters was determined using the Elbow Method and validated using the Davies-Bouldin Index, both supporting K=3. The clustering grouped the 514 regencies/cities into 117 regions with relatively low facility conditions, 302 with relatively moderate conditions, and 95 with relatively high conditions, with the low cluster concentrated in eastern Indonesia, particularly Papua and Maluku. The main contribution of this research is a data-driven cluster map that education authorities can use as an evidence-based reference for prioritizing budget allocation and infrastructure development toward regencies/cities in the low cluster, as well as a replicable scoring-normalization-clustering pipeline adaptable for future studies with additional indicators.

Downloads

Download data is not yet available.

References

[1] S. A. Nurfatimah, S. Hasna, and D. Rostika, “Membangun Kualitas Pendidikan di Indonesia dalam Mewujudkan Program Sustainable Development Goals (SDGs),” J. Basicedu, vol. 6, no. 4, pp. 6145–6154, 2022, doi: https://doi.org/10.31004/basicedu.v6i.

[2] M. T. Wardani, V. O. Ramadhani, N. Anggreani, Sumanto, and A. D. Kuswanto, “Pengelompokkan Provinsi Berdasarkan Kelayakan Ruang Kelas dan Tenaga Kependidikan Sekolah Dasar Menggunakan Algoritma K-Means: Analisi Data Periode 2023-2024,” Riau J. Tek. Inform., vol. 4, no. 2, pp. 163–172, 2025, doi: 10.30606/rjti.v4i2.3389.

[3] “Statistik Sekolah Dasar SD Tahun 2024/2025,” Kementerian Pendidikan Dasar dan Menengah. Accessed: Jun. 25, 2026. [Online]. Available: https://www.kemendikdasmen.go.id/en

[4] A. Edo and M. Yasin, “Dampak Kesenjangan Akses Pendidikan dan Faktor Ekonomi Keluarga terhadap Mobilitas Sosial,” J. Ilmu Pendidik. Sos., vol. 2, no. 3, pp. 317–326, 2024, doi: 10.71382/sinova.v2i3.175.

[5] N. Wijaya, “Performa Algoritma K-Means dan Fuzzy C-Means Dalam Analisis Klaster Pendidikan di Tingkat Kecamatan Jakarta,” Jurnal Komputer dan Informatika. Accessed: Jun. 25, 2026. [Online]. Available: https://journal.untar.ac.id/index.php/JKI/article/view/34485

[6] S. Maryam, R. Astuti, and F. M. Basysyar, “Optimalisasi Jumlah Cluster Data Sekolah Dasar (Sd) Menggunakan Algoritma K-Means Clustering,” JATI (Jurnal Mhs. Tek. Inform., vol. 7, no. 6, pp. 3640–3646, 2024, doi: 10.36040/jati.v7i6.8246.

[7] M. A. Irwansyah, Y. N. Alinda, R. N. Aini, and I. A. Alfitrah, “Analisis K-Means Dengan Rapidminer Untuk Klasifikasi Kualitas Pendidikan Sek olah Dasar Di Indonesia,” Zo. J. Sist. Inf., vol. 7, no. 1, pp. 1008–1020, 2025, doi: doi: 10.31849/a0hhsc57.

[8] M. D. Salman et al., “Perbandingan Kinerja Algoritma Clustering K-Means dan K-Medoids dalam Pengelompokan Sekolah di Provinsi Riau Berdasarkan Ketersediaan Sarana dan Prasarana,” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 5, no. 3, pp. 797–806, 2025, doi: 10.57152/malcom.v5i3.1950.

[9] K. Emilia, A. S. Rahayu, D. P. Yuliani, D. A. Prasetya, and P. A. Riyantoko, “Application of K-Means Clustering for Regency/City Clustering in East Java Based on 2024 Human Development Index Indicators,” J. Apl. Sains Data, vol. 1, no. 2, pp. 85–95, 2025, doi: 10.33005/jasid.v1i2.21.

[10] K. E. Setiawan and A. Kurniawan, “Pengelompokan Rumah Sakit di Jakarta Menggunakan Model DBSCAN, Gaussian Mixture, dan Hierarchical Clustering,” J. Inform. Terpadu, vol. 9, no. 2, pp. 149–156, 2023, doi: https://doi.org/10.54914/jit.v9i2.995.

[11] M. Faisal, J. Ilham Saputro, and W. Sri Utami, “Analysis Cluster K-Means Terhadap Fasilitas Sekolah Pada Tiap Provinsi Republik Indonesia,” Bull. Inf. Technol., vol. 6, no. 4, pp. 408–416, 2025, doi: 10.47065/bit.v5i2.2340.

[12] D. Yanto, H. Susanto, K. Zulkifli, and F. R. Gupron, “Penerapan Algoritma K-Means Dalam Menentukan Kualitas Satuan Pendidikan Berdasarkan Nilai Internal Dan Eksternal,” JEECOM J. Electr. Eng. Comput., vol. 5, no. 2, pp. 319–328, 2023, doi: 10.33650/jeecom.v5i2.6946.

[13] F. Bolikulov, R. Nasimov, A. Rashidov, F. Akhmedov, and Y. I. Cho, “Effective Methods of Categorical Data Encoding for Artificial Intelligence Algorithms,” Mathematics, vol. 12, no. 16, pp. 1-21, 2024, doi: 10.3390/math12162553.

[14] P. Koukaras and C. Tjortjis, “Data Preprocessing and Feature Engineering for Data Mining: Techniques, Tools, and Best Practices,” AI, vol. 6, no. 10, pp. 1–40, 2025, doi: 10.3390/ai6100257.

[15] R. R. Laska and A. M. Yolanda, “A Comparative Study of Z-Score and Min-Max Normalization for Rainfall Classification in Pekanbaru,” J. Data Sci., vol. 2024, no. 4, pp. 1–8, 2024, doi: 10.61453/jods.v2024no04.

[16] Y. Hasan, “Pengukuran Silhouette Score dan Davies-Bouldin Index pada Hasil Cluster K-Means dan Dbscan,” KAKIFIKOM (Kumpulan Artikel Karya Ilmiah Fakultas Ilmu Komputer). Accessed: Jun. 25, 2026. [Online]. Available: https://ejournal.ust.ac.id/index.php/KAKIFIKOM/article/view/3938

[17] R. S. T. Sihombing, “Pemerataan Pendidikan: Studi Kasus 34 Provinsi di Indonesia,” Parahyangan Econ. Dev. Rev., vol. 1, no. 2, pp. 143–151, 2023, doi: 10.26593/pedr.v1i2.6670.

[18] B. Hakim, F. J. Kaunang, C. Susanto, J. Salim, and R. Indradjaja, “Implementasi Machine Learning Dalam Pengelompokan Musik Menggunakan Algoritma K-Means Clustering,” IDEALIS Indones. J. Inf. Syst., vol. 8, no. 1, pp. 74–83, 2025, doi: 10.36080/idealis.v8i1.3357.

[19] T. A. J. Harahap and C. B. Santoso, “Analisis Tren Lowongan Pekerjaan Software Engineering Di Indonesia Dengan Clustering Dan Social Network Analysis,” IDEALIS Indones. J. Inf. Syst., vol. 8, no. 2, pp. 160–171, 2025, doi: 10.36080/idealis.v8i2.3518.