Customer segmentation with RFM models and demographic variable using DBSCAN algorithm

The aims of this research was to identify prospective customers by conducting customer segmentation based on recency, frequency, monetary (RFM) values and demographic variables. step were selected the data normalized. normalized clustered using density spatial clustering applications with noise (DBSCAN) algorithm. k-dist graph utilized RStudio tools best for epsilon MinPts. outcome utilizing 0.06 MinPts 3 identification 5 clusters 31 points considered as noise, resulting in a silhouette index (SI) value 0.4222. Based average RFM values, cluster 1 categorized customers, while 2, 3, 4, designated loyal customers. Furthermore, according analysis, majority are between ages 35 45, female, married, housewives. Women, groceries, such rice cooking oil, most popular products. Besides, mostly lecturers lived Pekanbaru. This compatible target people from upper middle class, lecturers, location mart well, which near campus.