Implementation of Data Mining Using K-Means Clustering Method to Determine Sales Strategy In S&R Baby Store

Abstract

The S&R Baby Store store is a Small and Medium Enterprise (SME) that is engaged in baby equipment, but there is a lot of competition between small and medium enterprises (SMEs) who are engaged in the same field, so that many products sold are of course not all sold out, some are lacking. in demand. Therefore the S&R Baby Store store needs a good sales strategy in order to increase sales profit. This study discusses the application of data mining, using the K-Means Clustering algorithm with the CRISP-DM method. Implementation using RapidMiner 9.10 which is done by entering sales transaction data with a total of 4 attributes and forming 4 clusters consisting of very in demand, in demand, moderate in demand and less in demand. the second cluster with 944 products, the third cluster with 2 products, and the fourth cluster with 43 products. The results of the cluster above are the products sold are the best-selling product categories, then the results of the cluster are validated using the Davies-Bouldin Index with a DBI value generated from clustering of 0.560.