Penerapan Algoritma K-Means untuk Mengetahui Pola Persediaan Barang pada Toko Raja Bekasi

Abstract

This study aims to determine how much the results of grouping goods affect the needs of consumers. Excess inventory will greatly fill the warehouse and be inefficient because of the expiration date on food products, beverages, etc. Currently Toko Raja still manages goods manually so it is not time efficient. To solve this problem, a technique is needed, namely data mining. The data mining technique that will be used in this research is the K-Means Clustering method. K-Means is one of the most popular algorithms because it is easy and simple to implement. However, the results of the clustering of K-Means are very dependent on the
selection of the initial cluster center point. Calculation of accuracy in this study using the test results of the K-Means clustering method using the Davies-Bouldin Index (DBI) is 1.856 where the DBI value close to zero cluster is good enough. From the resulting accuracy, it can be concluded that the K-Means Clustering method can support the system well.