K-Medoids Clustering of Regencies and Cities in North Sumatra Province Based on Food Security Indicators with C-Index Validation and ArcGIS Mapping

Balqis Indriyana; Riri Syafitri Lubis

doi:10.56427/jcbd.v6i1.1118

Authors

Balqis Indriyana Universitas Islam Negeri Sumatera Utara
Riri Syafitri Lubis Universitas Islam Negeri Sumatera Utara

DOI:

https://doi.org/10.56427/jcbd.v6i1.1118

Keywords:

K-Medoids, C-Index, ArcGIS, Food security, North Sumatra

Abstract

Food security varies considerably across the regencies and cities of North Sumatra Province. This study groups the 33 regencies and cities based on twelve food security indicators, determines the optimal number of clusters, and maps their spatial distribution using ArcGIS. A quantitative descriptive-analytical approach was applied to secondary data for 2025 from national and provincial agencies. The analysis involved multicollinearity screening using the Variance Inflation Factor (VIF), Z-score standardization, K-Medoids clustering with Euclidean distance, C-Index validation for K = 2 to 6, and spatial visualization. All twelve indicators had VIF values below 10 (maximum 7.10) and were retained. The K = 4 configuration produced the lowest C-Index (0.1406), yielding four clusters of 18, 3, 7, and 5 regencies/cities. Cluster 4, comprising the entire Nias Islands, was the most vulnerable on eight of twelve indicators, notably poverty, access to clean water, women's years of schooling, the Expected Food Pattern score, and local government rice reserves. The spatial map shows that indicator similarity does not always correspond to geographic proximity, as members of the same cluster are often spatially dispersed. These findings provide an initial basis for designing food security policies tailored to the characteristics of each regional group.

Downloads

Download data is not yet available.

References

[1] J. Clapp, W. G. Moseley, B. Burlingame, and P. Termine, “Viewpoint: The case for a six-dimensional food security framework,” Food Policy, vol. 106, Art. no. 102164, Jan. 2022, doi: 10.1016/j.foodpol.2021.102164.

[2] J. Neilson and J. Wright, “The state and food security discourses of Indonesia: Feeding the bangsa,” Geographical Research, vol. 55, no. 2, pp. 131–143, May 2017, doi: 10.1111/1745-5871.12210.

[3] Badan Pangan Nasional, Peta Ketahanan dan Kerentanan Pangan (Food Security and Vulnerability Atlas) Indonesia 2025 (in Indonesian). Jakarta, Indonesia: Badan Pangan Nasional, 2025. Accessed: Nov. 7, 2026. [Online]. Available: https://fsva.badanpangan.go.id

[4] M. S. Mutthaqin, Y. S. J. Nasution, and F. A. Lubis, “Food commodity development strategy towards food security in North Sumatra,” Dinasti International Journal of Economics, Finance & Accounting, vol. 5, no. 3, pp. 1806–1814, Aug. 2024, doi: 10.38035/dijefa.v5i3.3012.

[5] Z. Zulaika, H. Cipta, and M. A. P. Siregar, “Pendekatan regresi spline multivariabel untuk pemodelan indeks ketahanan pangan Provinsi Sumatera Utara” (in Indonesian), Proximal: Jurnal Penelitian Matematika dan Pendidikan Matematika, vol. 7, no. 1, pp. 387–400, May 2024, doi: 10.30605/proximal.v7i2.3666.

[6] M. Z. Rodriguez et al., “Clustering algorithms: A comparative approach,” PLOS ONE, vol. 14, no. 1, Art. no. e0210236, Jan. 2019, doi: 10.1371/journal.pone.0210236.

[7] W. Afriani and F. Rakhmawati, “Multi-objective EV routing with recharging, battery-swapping, and K-Means station siting for ride-hailing fleets in Medan City,” Journal of Computers and Digital Business, vol. 5, no. 3, pp. 300–311, Aug. 2026, doi: 10.56427/jcbd.v5i3.1054.

[8] L. Kaufman and P. J. Rousseeuw, Finding Groups in Data: An Introduction to Cluster Analysis. New York, NY, USA: John Wiley & Sons, 1990, doi: 10.1002/9780470316801.

[9] E. Schubert and P. J. Rousseeuw, “Fast and eager k-medoids clustering: O(k) runtime improvement of the PAM, CLARA, and CLARANS algorithms,” Information Systems, vol. 101, Art. no. 101804, Nov. 2021, doi: 10.1016/j.is.2021.101804.

[10] A. M. Ikotun, A. E. Ezugwu, L. Abualigah, B. Abuhaija, and J. Heming, “K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data,” Information Sciences, vol. 622, pp. 178–210, Apr. 2023, doi: 10.1016/j.ins.2022.11.139.

[11] M. Charrad, N. Ghazzali, V. Boiteau, and A. Niknafs, “NbClust: An R package for determining the relevant number of clusters in a data set,” Journal of Statistical Software, vol. 61, no. 6, pp. 1–36, Nov. 2014, doi: 10.18637/jss.v061.i06.

[12] T. Saifudin et al., “Mapping food insecurity: Spatial modelling of undernourishment prevalence in Indonesia using geographically weighted regression,” Jurnal Teori dan Aplikasi Matematika, vol. 9, no. 4, pp. 1165–1181, Oct. 2025, doi: 10.31764/jtam.v9i4.32063.

[13] R. Alfarizal, S. F. Thahar, S. I. Mardani, S. M. Ramadhan, L. P. Marpaung, and T. H. Siagian, “Model-based approach for clustering regencies/cities in the Land of Papua based on food security indicators,” Jurnal Ilmu Pertanian Indonesia, vol. 30, no. 1, pp. 19–30, Dec. 2024, doi: 10.18343/jipi.30.1.19.

[14] T. Zhafira, B. Bustami, and N. Nunsina, “Clustering of food security levels in North Aceh using K-Medoids,” Journal of Applied Informatics and Computing, vol. 10, no. 3, pp. 2476–2488, Jun. 2026, doi: 10.30871/jaic.v10i3.12881.

[15] S. Robiati, D. Fitria, D. Vionanda, and D. Sulistiowati, “Comparison of K-Means and K-Medoids in clustering regency/city in West Sumatra Province based on environmental indicators,” Indonesian Journal of Statistics and Its Applications, vol. 8, no. 2, pp. 191–201, Dec. 2024, doi: 10.29244/ijsa.v8i2p191-201.

[16] M. Mathenge, B. G. J. S. Sonneveld, and J. E. W. Broerse, “Mapping the spatial dimension of food insecurity using GIS-based indicators: A case of Western Kenya,” Food Security, vol. 15, no. 1, pp. 243–260, Feb. 2023, doi: 10.1007/s12571-022-01308-6.

[17] Badan Pusat Statistik Provinsi Sumatera Utara, Provinsi Sumatera Utara dalam Angka 2025 (in Indonesian). Medan, Indonesia: BPS Provinsi Sumatera Utara, 2025. Accessed: Nov. 7, 2026. [Online]. Available: https://sumut.bps.go.id/id/publication/2025/02/28/eb64d25aa56a75d579156d6a/provinsi-sumatera-utara-dalam-angka-2025.html

[18] J. H. Kim, “Multicollinearity and misleading statistical results,” Korean Journal of Anesthesiology, vol. 72, no. 6, pp. 558–569, Dec. 2019, doi: 10.4097/kja.19087.

[19] L. B. V. de Amorim, G. D. C. Cavalcanti, and R. M. O. Cruz, “The choice of scaling technique matters for classification performance,” Applied Soft Computing, vol. 133, Art. no. 109924, Jan. 2023, doi: 10.1016/j.asoc.2022.109924.

[20] L. J. Hubert and J. R. Levin, “A general statistical framework for assessing categorical clustering in free recall,” Psychological Bulletin, vol. 83, no. 6, pp. 1072–1080, Nov. 1976, doi: 10.1037/0033-2909.83.6.1072.

[21] T. Beal, A. Tumilowicz, A. Sutrisna, D. Izwardy, and L. M. Neufeld, “A review of child stunting determinants in Indonesia,” Maternal & Child Nutrition, vol. 14, no. 4, Art. no. e12617, Oct. 2018, doi: 10.1111/mcn.12617.