Customer Profiling dengan Menggunakan Metode K-Means Euclidean Distance di BPJS Ketenagakerjaan Tanjung Perak


  • Anastasya Febiyati Ayutrisula UIN Sunan Ampel Surabaya
  • Aris Fanani UIN Sunan Ampel Surabaya


Data Mining; Clustering; K-Means; Euclidean Distance; Customer Profiling


Basically humans need social security to ensure the safety of their lives and be able to fulfill their daily needs. Therefore, humans need insurance in the form of a guarantee program and companies need to do a way to group customers based on the characteristics they have or what is known as customer profiling. In this study the clustering method using the k-means euclidean distance algorithm was used. Before processing data, data needs to be normalized first, then the data is processed into several clusters. Data that has been clustered will produce a category that will be used in the customer profiling process. From this research, the first cluster included in high-paying customers was the tendency to choose the JKM, JHT program and for the second cluster included in the low-wage customer with a tendency to choose the JKK program, JKM. With this research, companies can find out the results of customer profiling to be able to take further action.


Download data is not yet available.