Analysis of Silhouette Coefficient Evaluation with Euclidean Distance in the Clustering Method (Case Study: Number of Public Schools in Indonesia)
Main Article Content
Abstract
This study aims to find out how much the silhouette coefficient value is obtained from calculating the distance from the data to the centroid using the euclidean distance in the k-means method and to provide input in science for further research in developing the k-means method. To solve this problem, researchers use the k-means method with silhouette coefficient evaluation. Where the data source in this study took data directly from the Indonesian Central Bureau of Statistics (BPS) in the form of softcopy entitled "Statistics of Indonesia 2021" with the URL: https://www.bps.go.id. The data used in this study uses 2020 data which consists of 34 provinces. The data will be processed using the k-means method with the silhouette coefficient using the euclidean distance. The results obtained are cluster = 4 which is the best cluster for classifying the number of public schools in Indonesia by province in 2020 with a silhouette coefficient of -0.9944. By doing research, it can provide input in science for further research in developing clustering methods, especially k-means.
Downloads
Article Details
[2] T. Imandasari, A. Wanto, And AP Windarto, "Analysis of Decision Making in Determining Pkl Students Using the Promethee Method," J. Ris. Comput., Vol. 5, No. 3, pp. 234–239, 2018.
[3] DA Silitonga, M. Anjelita, And AP Windarto, "Fuzzy Inference System on Prediction of Pertamax Fuel Purchases at gas stations in Pematangsiantar City," Syntax J. Inform., Vol. 8, No. 2, P. 75, 2019, Doi: 10.35706/Syji.V8i2.1841.
[4] K. Handoko, "Application of Data Mining in Improving the Quality of Learning in Higher Education Institutions Using the K - Means Clustering Method (Case Study in the Tkj Study Program at the South Solok Community Academy)," Teknosi, Vol. 2, No. 3, pp. 31–40, 2016.
[5] AP Windarto, MR Lubis, And Solikhun, "Neural Network Architectural Models with Backpropogation in Total Profit Prediction," Gathered. J. Computing Science., Vol. 5, No. 2, pp. 147–158, 2018.
[6] MRL Iin Parlina, Agus Perdana Windarto, Anjar Wanto, "Utilizing the K-Means Algorithm in Determining Eligible Employees to Take the Assessment Center," Utilizing the Algorithm. K-Means In Determining Eligible Employees To Follow Asessment Cent. For Clusts. program SDP, Vol. 3, No. 1, pp. 87–93, 2018.
[7] A. Aditya, I. Jovian, and BN Sari, "Implementation of K-Means Clustering for National Junior High School Examinations in Indonesia in 2018/2019," J. Media Inform. Budidarma, Vol. 4, pp. 51–58, 2020, Doi: 10.30865/Mib.V4i1.1784.
[8] MG Sadewo, AP Windarto, And D. Hartama, "Application of Datamining in Broiler Populations in Indonesia by Province Using K-Means Clustering," Infotekjar (Jurnal Nas. Inform. And Teknol. Network), Vol. 2, No. 1, pp. 60–67, 2017, Doi: 10.30743/Infotekjar.V2i1.164.
[9] H. Sulastri And AI Gufroni, "Application of Data Mining in Grouping Patients with Thalassemia," J. Nas. Technol. And Sist. Inf., Vol. 3, No. 2, pp. 299–305, 2017, Doi: 10.25077/Teknosi.V3i2.2017.299-305.
[10] S. Butsianto And NT Mayangwulan, "Application of Data Mining to Predict Car Sales Using the K-Means Clustering Method," J. Nas. Computing And Technology. Inf., Vol. 3, No. 3, pp. 187–201, 2020.
[11] AP Tiratana, B. Mulyawan, And MD Lauro, "Development of Web-Based Customer Relationship Management Applications Using the K-Means Method," J. Computer Science. And Sist. Inf., Pp. 179–184, 2019.
[12] S. Asmiatun, N. Wakhidah, AN Putri, U. Semarang, and K. Jalan, "Application of the K-Medoids Method for Classifying Road Conditions in the City of Semarang 1.2," J. Tek. inform. And Sist. Inf., Vol. 6, No. 2, 2020.
[13] EF Sirat, BD Setiawan, And F. Ramdani, "A Comparative Analysis of the K-Means and Isodata Algorithms for Clustering Data on Hot Spots in the Sumatra Region in 2001 to 2014," J. Pemmb. Technol. inf. And Computing Science., Vol. 2, No. 11, pp. 5105–5112, 2018.
[14] N. Rahmawati, YN Nasution, And FDT Amijaya, "Dataminingmarket Basket Analysis Application to Find Purchase Patterns at the Main Metro Stores in Balikpapan," J. Exponential, Vol. 8, No. 2012, pp. 1–8, 2017.
[15] R. Setiawan, "Application of Data Mining Using the K-Means Clustering Algorithm to Determine New Student Promotion Strategies (Case Study: Polytechnic Lp3i Jakarta)," J. Lentera Ict, Vol. 3, No. 1, pp. 76–92, 2016.
[16] F. Selva And D. Pratama, "Identification of Clusters of Working Age Population in South Sumatra Province Using K-Modes," J. Politek. Caltex Riau, Vol. 4, No. 1, pp. 1–9, 2018.
[17] DP Sinaga, PP Adikara, And YA Sari, "Clusterization of Hot Spot Data Using the Self Organizing Map Method in the Java Region," J. Pemmb. Technol. inf. And Computing Science., Vol. 3, No. 10, pp. 9543–9551, 2019.
[18] K. Sari, "Analysis of Evaluating Distance Calculations for Silhouette Coefficient Values in the K-Means Algorithm," Thesis, 2020.
[19] M. Nishom, "Comparison of the Accuracy of Euclidean Distance, Minkowski Distance, and Manhattan Distance in the Chi-Square-Based K-Means Clustering Algorithm," Vol. 4, No. 1, pp. 20–24, 2019, Doi: 10.30591/Jpit.V4i1.1253.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.