Klasterisasi Stok Produk Retail Untuk Menetukan Pergerakan Kebutuhan Konsumen Dengan Algoritma K-Means

Abstract

− Retail product clustering is a product arrangement that is adjusted to the flow of placement or this layout is more suitable for product placement according to standards. Utilization of existing data through the clustering method approach can be applied in analyzing product grouping of data on availability and inventory of goods in warehouses so that it can provide knowledge and information. The clustering method is processed using the K-Means algorithm, where the results also show a new insight, namely grouping products based on 3 clusters. Cluster 1 is a product category with low availability or Low, namely 939 out of 1000 availability categories based on the number of products tested, then cluster 2 is a product category with medium or Medium availability, namely 51 out of 1000 availability categories based on the number of products tested, and finally cluster 3 is a product category with fairly high availability or High, namely 10 out of 100 availability categories based on the number of products tested. Tests using Rapid Miner tools can also produce similar insights, namely that each cluster has cluster group members according to manual calculations such as Cluster_0 in Rapid Miner has 51 cluster members representing the Medium cluster, Cluster_1 has 939 cluster group members representing the Low cluster, and Cluster_2 has 10 cluster members corresponding to the cluster representation High.