DETERMINATION THE BEST NUMBER OF CLUSTERS IN K-MEANS FOR SEEING CLUSTERING PATTERN OF GRADUATES DATA
DOI:
https://doi.org/10.33387/jati.v2i1.60Keywords:
clustering, k-means, elbow, sse, graduationAbstract
The success of K-Means in analyzing data can be seen from the grouping formed based on the number of clusters specified. The algorithm used by K-Means in determining the number of clusters is selected randomly, this can cause the results of the clusters formed to be not optimal. To determine the optimal number of clusters, so the research was conducted using the Elbow method. Elbow is one of the methods that can be used for determining the best number of clusters by representation of the graph that results from the Sum of Square Error (SSE) calculation. The research was conducted using a dataset with parameters of GPA value and the number of credits for clustering the graduation time with a range of 9 clusters. Grouping data with a range of 9 clusters using K-Means it resulted that data keep on change the clusters, depending on the number of clusters specified. Each cluster formed from a range of 9 clusters is used on SSE calculations to determine the best number of clusters with representation using an Elbow graph. Based on the results of the SSE calculation, it obtained that the best number of clusters in this research was 2 clusters with an SSE difference value of 4611.379920 and it managed to form an Elbow line on the graph. Data grouping based on the number of optimal clusters for clustering the graduation time consists of cluster 1 as many as 199 data as a timely cluster and cluster 2 as many as 41 data as an untimely cluster.
References
Waworuntu, M. N. V., & Amin, M. F. (2018). Penerapan Metode K-Means Untuk Pemetaan Calon Penerima Jamkesda. KLIK- Kumpulan Jurnal Ilmu Komputer, 5(2), 190- 200. (http://dx.doi.org/10.20527/klik.v5i2.157) diakses 12 januari 2022.
Trayasiwi, G. P. (2017). Penerapan Metode Klastering dengan Algoritma k-Means Untuk Prediksi Kelulusan Mahasiswa Pada Program Studi Teknik Informatika Strata Satu. UDiNus Repos, 1(1), 1-11.
KeyUA, 2021. “10 Popular Data Mining Algorithms”. Tersedia
[https://keyua.org/blog/top-10-data-mining- algorithms/] diakses 20 Desember 2021.
Syakur, M. A., Khotimah, B. K., Rochman,
E. M. S., & Satoto, B. D. (2018, April). Integration k-means clustering method and elbow method for identification of the best customer profile cluster. In IOP conference series: materials science and engineering (Vol. 336, p. 012017). IOP Publishing.(10.1088/1757- 899X/336/1/012017) diakses 12 januari 2022.
Dubey, A. K., Gupta, U., & Jain, S. (2018). Comparative study of K-means and fuzzy C- means algorithms on the breast cancer data. International Journal on Advanced Science, Engineering and Information Technology, 8(1), 18-29.
(http://dx.doi.org/10.18517/ijaseit.8.1.3490) diakses tanggal 12 januari 2022.
Jannah, A. R., Arifianto, D., & Kom, M. 2017. “Penerapan Metode Clustering dengan Algoritma K-Means untuk Prediksi Kelulusan Mahasiswa Jurusan Teknik Informatika di Universitas Muhammadiyah Jember”. Jurnal Manajemen Sistem Informasi an Teknologi, 1(1210651237), 1–10.
<http://repository.unmuhjember.ac.id/id/eprin t/589>
Studio, M. (2018). Pengelompokan Data Penjualan Aksesoris Menggunakan Algoritma K-Means. vol. IV, (2), 401-411.
Aditya, K. B., Puspitaningrum, D., & Setiawan, Y. (2017). Sistem Informasi Geografis Pemetaan Faktor-Faktor Yang Mempengaruhi Angka Kematian Ibu (Aki) Dan Angka Kematian Bayi (AKB) Dengan Metode K-Means Clustering (Studi Kasus: Provinsi Bengkulu). Jurnal Teknik
Informatika UIN Syarif Hidayatullah, 10(1), 133712.
(http://dx.doi.org/10.15408/jti.v10i1.6817) diakses 21 januari 2022.
Duong, M. Q., Lam, B. L. H., Tu, G. Q. H., & Hieu, N. H. (2019). Combination of K- Mean clustering and elbow technique in mitigating losses of distribution network. GMSARN International, 13, 153-158.
Priyatman, H., Sajid, F., & Haldivany, D. (2019). Klasterisasi Menggunakan Algoritma K-Means Clustering untuk Memprediksi Waktu Kelulusan Mahasiswa. Jurnal Edukasi Dan Penelitian Informatika (JEPIN), 5(1), 62. (http://dx.doi.org/10.26418/jp.v5i1.29611) diakses 21 januari 2022.
Eldo, H. (2020). Penentuan Cluster Terbaik K-Means Menggunakan Algoritma Silhouette (Doctoral dissertation, Universitas Sumatera Utara) http://repositori.usu.ac.id/handle/123456789/ 27537.
Santoso, T., & Saftarina, F. 2020. “Klasterisasi Petani Padi Sawah di Kota Metro Provinsi Lampung Menggunakan Algoritma K-Means Cluster dan Elbow Method”. Journal of Agribusiness and Community Empowerment, 3(1), 37–43. http:doi.org/2655- 4526/26552965/jace/11.10.2019.
Putu, N., Merliana, E., & Santoso, A. J. (2015). “Analisa Penentuan Jumlah Cluster Terbaik pada Metode K-Means”. 978–979. https://doi.org/10.22146/ijccs.6641
Dewi, D. A. I. C., & Pramita, D. A. K. (2019). Analisis Perbandingan Metode Elbow dan Silhouette pada Algoritma Clustering K- Medoids dalam Pengelompokan Produksi Kerajinan Bali. Matrix: Jurnal Manajemen Teknologi Dan Informatika, 9 (3), 102–109 http://dx.doi.org/10.31940/matrix.v9i3.1662.
Nainggolan, R., Perangin-Angin, R., “Simarmata, E., & Tarigan, A. F. 2019. Improved the Performance of the K-Means Cluster Using the Sum of Squared Error (SSE) optimized by using the Elbow Method”. Journal of Physics: Conference Series, 1361(1). https://doi.org/10.1088/1742- 6596/1361/1/012015.
Qi, J., Yu, Y., Wang, L., & Liu, J. (2016, October). K-means: An effective and efficient K-means clustering algorithm. In 2016 IEEE international conferences on big data and cloud computing (BDCloud), social computing and networking (SocialCom), sustainable computing and communications (SustainCom)(BDCloud-SocialCom- SustainCom) (pp. 242-249). IEEE 10.1109/BDCloud-SocialCom- SustainCom.2016.46.
Downloads
Published
Issue
Section
License
Copyright (c) 2023 Jurnal Jaringan dan Teknologi Informasi
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
