Abstract
Supermarkets are shopping places that provide various daily necessities. Many customers visit supermarkets to buy necessities. The growth of supermarkets is increasing. Supermarkets have a variety of products with different brands, branches, and types of customers. To create a sales strategy, need to know the products that customers are interested in. In this research, supermarket product clustering was carried out based on sales data. The clustering algorithm used in this research is the DBSCAN algorithm. This algorithm is an algorithm for grouping data objects based on density, which is influenced by input parameters, namely the Eps and MinPts values. The data used in this research is secondary data consisting of 100 supermarket sales data, taking 2 attributes. The clustering results show that using the Eps parameter value = 6 and the MinPts value = 9, the product data is divided into 3 clusters, namely cluster 1 of products that are not in demand, cluster 2 of products that are in demand and cluster 3 of very popular products.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call