Implementation Of ETL E-Commerce For Customer Clustering Using RFM And K-Means Clustering

Abstract

E-commerce is the activity of selling and buying goods through an online system or online. One of the business models in which consumers sell products to other consumers is the Customer to Customer (C2C) business model. One of the things that need to be considered in this business model is knowing the level of customer loyalty. By knowing the level of customer loyalty, the company can provide several different treatments to its customers so that they can maintain good relations with customers and can increase product purchase revenue. In this study, the author wants to segment customers on data in E-commerce companies in Brazil using the K-Means clustering algorithm using the RFM (Recency, Frequency, Monetary) feature. There are also several ETL stages of research that must be carried out, namely taking data from the open public data site (Kaggle), which consist of more than 9 tables (extract), then merging the data to select some data that needs to be used (transform and load), understanding data by displaying it in graphic form, conducting data selection to select features / attributes. which is in accordance with the proposed method, performs data preprocessing, and creates a model to get the cluster. Based on the results of the research that has been done, the number of clusters is 4 clusters with the evaluation value of the model using the silhouette score is 0.470.