Cluster Analysis of Provinces Based on the Prevalence of Undernourishment Using the K-Means Algorithm

Lana Astria; Santi Meliani; Ade Pratama; Abdul Rohman

doi:10.35457/9wjmrq51

Authors

Lana Astria Universitas Ngudi Waluyo
Santi Meliani Universitas Ngudi Waluyo
Ade Pratama Universitas Ngudi Waluyo
Abdul Rohman Universitas Ngudi Waluyo

DOI:

https://doi.org/10.35457/9wjmrq51

Keywords:

Cluster, Data Mining, Food Security, K-Means, Prevalence of Undernourishment

Abstract

Food security is a fundamental prerequisite for human development, and Indonesia still faces wide disparities in the Prevalence of Undernourishment (PoU) across provinces. This study aims to group 38 Indonesian provinces based on their average PoU for the 2018-2024 period using the K-Means Clustering algorithm to support evidence-based food security policy prioritization. Secondary PoU data compiled from official statistics underwent data cleaning (correction of naming and regional code inconsistencies), z-score standardization, and optimal cluster determination through a combination of the Elbow Method, Silhouette Score, and Davies-Bouldin Index. The analysis identified three optimal clusters (Silhouette Score = 0.593): a low-risk cluster (26 provinces, mean PoU 7.85%), a moderate-risk cluster (6 provinces, mean PoU 17.16%), and a high-risk cluster (6 provinces, mean PoU 32.13%) dominated by provinces in Papua and Maluku. This study contributes a methodological framework for handling administrative data inconsistencies arising from regional redistricting, as well as a nutrition-intervention priority map that can serve as a reference for policymakers in achieving SDG 2 (Zero Hunger).

References

Ashabi, A., Sahibuddin, S. B., & Haghighi, M. S. (2020). The Systematic Review of K-Means Clustering Algorithm. Proceedings 9th International Conference on Networks, Communication and Computing (ICNCC 2020), Tokyo, Japan. https://doi.org/10.1145/3447654.3447657

Ashari, F., Nugroho, E. D., Baraku, R., Yanda, I. N., & Liwardana, R. (2023). Analysis of Elbow, Silhouette, Davies-Bouldin, Calinski-Harabasz, and Rand-Index Evaluation on K-Means Algorithm for Classifying Flood-Affected Areas in Jakarta. Journal of Applied Informatics and Computing, 7(1), 95-103. https://doi.org/10.30871/jaic.v7i1.4947

Ahmed, M., Seraj, R., & Islam, S. M. S. (2020). The k-means algorithm: A comprehensive survey and performance evaluation. Electronics, 9(8), 1-12. https://doi.org/10.3390/electronics9081295

Ayalew, M. M., Dessie, Z. G., Zewotir, T., & Mitiku, A. A. (2024). Exploring the spatial and spatiotemporal patterns of severe food insecurity across Africa (2015-2021). Scientific Reports, 14(29846), 1-14. https://doi.org/10.1038/s41598-024-78616-8

Bahauddin, A., Fatmawati, A., & Sari, F. P. (2021). Analisis Clustering Provinsi Di Indonesia Berdasarkan Tingkat Kemiskinan Menggunakan Algoritma K-Means. Jurnal Manajemen Informatika dan Sistem Informasi, 4(1), 1-8. https://doi.org/10.36595/misi.v4i1.216

Castelli, T., Mocenni, C., & Dimitri, G. M. (2024). A machine learning approach to assess Sustainable Development Goals food performances: The Italian case. PLOS One, 19(1), 1-20. https://doi.org/10.1371/journal.pone.0296465

Chong, B. (2021). K-means clustering algorithm: a brief review. Academic Journal of Computing & Information Science, 4(5), 37-40. https://doi.org/10.25236/AJCIS.2021.040506

Bajal, E., Katara, V., Bhatia, M., & Hooda, M. (2022). A Review of Clustering Algorithms: Comparison of DBSCAN and K-mean with Oversampling and t-SNE. Recent Patents on Engineering, 16(2), 1-15. https://doi.org/10.2174/1872212115666210208222231

Clark, A. Y., Blumenfeld, N., Lal, E., Darbari, S., Northwood, S., & Wadpey, A. (2021). Using k-means cluster analysis and decision trees to highlight significant factors leading to homelessness. Mathematics, 9(17), 2021, 1-14. https://doi.org/10.3390/math9172045

Food and Agriculture Organization of the United Nations. (2024). Indicator 2.1.1 - Prevalence of undernourishment. https://www.fao.org/sustainable-development-goals-data-portal/data/indicators/2.1.1-prevalence-of-undernourishment/en

Febriansyah, F. & Muntari, S. (2023). Penerapan Algoritma K-Means untuk Klasterisasi Penduduk Miskin pada Kota Pagar Alam. JISKa: Jurnal Informatika Sunan Kalijaga, 8(1), 66-77. https://doi.org/10.14421/jiska.2023.8.1.66-77

Han, J., Kamber, M., & Pei, J. (2012). Data Mining: Concepts and Techniques, 3rd ed. Burlington, MA, USA: Morgan Kaufmann.

Maori, N. A. & Evanita, E. (2023). Metode Elbow dalam Optimasi Jumlah Cluster pada K-Means Clustering. Simetris: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer, 14(2), 277-288. https://doi.org/10.24176/simet.v14i2.9630

Marcelina, D., Kurnia, A., & Terttiaavini, T. (2023). Analisis Klaster Kinerja Usaha Kecil dan Menengah Menggunakan Algoritma K-Means Clustering. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 3(2), 293-301. https://doi.org/10.57152/malcom.v3i2.952

Matdoan, M. Y., Igo, L., Rumeon, R., Fadhilah, R, & Laamena, N. S. (2024). Penerapan Algoritma K-Means Untuk Klusterisasi Kabupaten/Kota Berdasarkan Tingkat Kemiskinan di Kepulauan Maluku dan Papua. Jurnal Sains Matematika dan Statistika, 10(1), 1-9. https://doi.org/10.24014/jsms.v10i1.21260

Mayasari, S. N. & Nugraha, J. (2023). Implementasi K-Means cluster analysis untuk mengelompokkan kabupaten/kota berdasarkan data kemiskinan di Provinsi Jawa Tengah tahun 2022. KONSTELASI: Konvergensi Teknologi dan Sistem Informasi, 3(2), 317-329. https://doi.org/10.24002/konstelasi.v3i2.7200

Oti, E. U., Olusola, M. O., Eze, F. C., & Enogwe, S. U. (2021). Comprehensive Review of K-Means Clustering Algorithms. IJASRE: International Journal of Advances in Scientific Research and Engineering, 7(8), 64-69, 2021. https://doi.org/10.31695/IJASRE.2021.34050

Pratiwi, G. R., Wahiddin, D., Awal, E. E., & Fauzi A. (2024). Klasterisasi tingkat kemiskinan kabupaten/kota di Indonesia menggunakan algoritma K-Means dan K-Medoids. Jurnal Algoritma, 21(2), 197-208.

Rahman, M. A., Sani, N. S., Hamdan, R., Othman, Z. A., & Bakar, A. A. (2021). A clustering approach to identify multidimensional poverty indicators for the bottom 40 percent group. PLOS One, 16(8), 1-25. https://doi.org/10.1371/journal.pone.0255312

Ritonga, P. K. & Hasibuan, M. S. (2025). Analisis Perbandingan Silhouette dengan Elbow pada Algoritma K-Means dan DBSCAN. METIK JURNAL, 9(1), 64-71. https://doi.org/10.47002/metik.v9i1.1027

Sari, F. D. R. & Ediwijoyo, S. P. (2023). Clustering Analysis Using K-Medoids on Poverty Level Problems in Central Java by District/City. KnE Social Sciences, 2023, 78-87. https://doi.org/10.18502/kss.v8i9.13321

Shi, C., Wei, B., Wei, S., Wang, W., Liu, H., & Liu, J. (2021). A quantitative discriminant method of elbow point for the optimal number of clusters in clustering algorithm. EURASIP Journal on Wireless Communications and Networking, 2021(31), 1-16. https://doi.org/10.1186/s13638-021-01910-w

Sofyan, H., Iqbal, M., Marzuki, M., & Muhammad, M. (2021). The comparison of k-modes clustering and ROCK clustering to the poverty indicator in Samadua Subdistrict, South Aceh. IOP Conference Series: Materials Science and Engineering, 1087(2021), 1-8. https://doi.org/10.1088/1757-899X/1087/1/012085

Suraya, G. R. & Wijayanto, A. W. (2022). Comparison of hierarchical clustering, k-means, k-medoids, and fuzzy c-means methods in grouping provinces in Indonesia according to the special index for handling stunting. Indonesian Journal of Statistics and Its Applications, 6(2), 180-201. https://doi.org/10.29244/ijsa.v6i2p180-201