Optimization of MSMEs Clustering in Sampang District Using K-Medoids Method and Silhouette Coefficient Method

Authors

  • Muhammad Iqbal Firmansyah Department of Information Systems, Universitas Trunojoyo Madura, Bangkalan, East Java, Indonesia
  • Yeni Kustiyahningsih Department of Information Systems, Universitas Trunojoyo Madura, Bangkalan, East Java, Indonesia
  • Eza Rahmanita Department of Information Systems, Universitas Trunojoyo Madura, Bangkalan, East Java, Indonesia
  • Mochammad Syahrul Abidin Department of Information Systems, Universitas Trunojoyo Madura, Bangkalan, East Java, Indonesia
  • Budi Dwi Satoto Department of Information Systems, Universitas Trunojoyo Madura, Bangkalan, East Java, Indonesia

DOI:

https://doi.org/10.34148/teknika.v14i1.1116

Keywords:

K-Medoids, Elbow, Silhoutte Coefficient, Clustering, Similarity

Abstract

Micro, Small, and Medium Enterprises (MSMEs) are an important sector in the economy, playing a significant role in creating jobs and driving local economic growth. This study aims to identify the business development patterns of MSMEs in Sampang District using the K-Medoids method. The background issue raised is the lack of appropriate segmentation for MSMEs, which complicates the efforts of the government and business actors in designing suitable development strategies. The dataset used consists of 1,276 MSME data points with six variables: Type of Business, Number of Workers, Production Capacity, Revenue, Assets, and Business License. The data processing steps include data conversion, one-hot encoding, and normalization to ensure uniformity. Clustering is performed using the Elbow method to determine the optimal number of clusters, with K=4 chosen as the optimal cluster number based on the highest Silhouette Coefficient value of 0.5662 compared to other K values. The Silhouette Coefficient values for K=2 are 0.3711, K=5 is 0.5389, K=7 is 0.5201, and K=9 is 0.4737. The clustering results show that this cluster encompasses various types of services, trade, to food and beverages sectors. This segmentation can support data-driven decision-making at the village level. Although this research shows promising results, it is recommended to expand the quantity and variety of data and consider external factors affecting MSME performance. Thus, this study makes a valuable contribution to understanding the business characteristics of MSMEs in Sampang District.

Downloads

Download data is not yet available.

References

[1] D. Azmi Fadhilah and T. Pratiwi, “Strategi Pemasaran Produk UMKM Melalui Penerapan Digital Marketing,” Coopetition J. Ilm. Manaj., vol. 12, no. 1, pp. 17–22, 2021, doi: 10.32670/coopetition.v12i1.279.

[2] D. K. Harjono, Tinjauan Terhadap Undang-Undang Nomor 11 Tahun 2020 Tentang Cipta Kerja. 2021.

[3] S. Setiawansyah, A. T. Priandika, B. Ulum, A. D. Putra, and D. A. Megawaty, “UMKM Class Determination Support System Using Profile Matching,” Bull. Informatics Data Sci., vol. 1, no. 2, p. 46, 2022, doi: 10.61944/bids.v1i2.37.

[4] F. M. Trisuciana, D. Witarsyah, E. Sutoyo, and J. M. Machado, “Clustering of COVID-19 Vaccination Recipients in DKI Jakarta Using the K-Medoids Algorithm,” Proc. - Int. Conf. Adv. Data Sci. E-Learning Inf. Syst. ICADEIS 2022, pp. 4–10, 2022, doi: 10.1109/ICADEIS56544.2022.10037509.

[5] S. Setioko, Y. Fitriani, and K. Munawaroh, “Strategi Peningkatan Usaha Kecil Mikro dan Menengah (UMKM) di Era Pandemi Covid-19 Pada Kota Metro,” J. Community Dev., vol. 2, no. 2, pp. 60–65, 2021, doi: 10.47134/comdev.v2i2.24.

[6] M. R. Adiyanto and E. Amaniyah, “Tingkat Kesadaran Sertifikat Halal Pelaku UMK di Pulau Madura,” AKSES J. Ekon. dan Bisnis, vol. 18, no. 2, pp. 94–101, 2023, doi: 10.31942/akses.v18i2.10123.

[7] Y. M. Riszinin and T. R. Dwi Adi Nugroho, “Preferensi Konsumen terhadap Pembelian Keripik Singkong di UD. Sumber Mutiara Kecamatan Sampang Kabupaten Sampang,” Agriscience, vol. 3, no. 1, pp. 58–71, 2022, doi: 10.21107/agriscience.v3i1.15209.

[8] A. S. Sunge, Y. Heryadi, Y. Religia, and Lukas, “Comparison of Distance Function to Performance of K-Medoids Algorithm for Clustering,” Proceeding - ICoSTA 2020 2020 Int. Conf. Smart Technol. Appl. Empower. Ind. IoT by Implement. Green Technol. Sustain. Dev., 2020, doi: 10.1109/ICoSTA48221.2020.1570615793.

[9] M. Lee, S. Lee, J. Park, and S. Seo, “Clustering and characterization of the lactation curves of dairy cows using K-medoids clustering algorithm,” Animals, vol. 10, no. 8, pp. 1–14, 2020, doi: 10.3390/ani10081348.

[10] Y. Kustiyahningsih, A. Khozaimi, and J. Purnama, “Pengelompokan UMKM Batik Madura Menggunakan Metode K-Means dan Sillhoutte Coefficient,” Teknika, vol. 13, no. 2, pp. 192–198, 2024, doi: 10.34148/teknika.v13i2.779.

[11] F. Nuraeni, D. Kurniadi, and G. Fauzian Dermawan, “Pemetaan Karakteristik Mahasiswa Penerima Kartu Indonesia Pintar Kuliah (KIP-K) menggunakan Algoritma K-Means++,” J. Sisfokom (Sistem Inf. dan Komputer), vol. 11, no. 3, pp. 437–443, 2023, doi: 10.32736/sisfokom.v11i3.1439.

Downloads

Published

2025-03-03

Issue

Vol. 14 No. 1 (2025): March 2025

Section

Articles

License

Copyright (c) 2025 Teknika

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

How to Cite

Optimization of MSMEs Clustering in Sampang District Using K-Medoids Method and Silhouette Coefficient Method. (2025). Teknika, 14(1), 1-8. https://doi.org/10.34148/teknika.v14i1.1116