CLUSTERING DATA PENJUALAN TOKO HELM KARTINI MENGGUNAKAN METODE K-MEANS

This study aims to design a K-Means clustering-based system that can help Kartini Helmet Store in grouping helmet sales data based on product category. With the increasing need for deeper data analysis to support business strategies, this store faces challenges in understanding sales patterns and customer preferences. This system utilizes the K-Means clustering algorithm implemented through the Python programming language to group sales data, facilitate trend analysis, and provide visualization of clustering results. The data used are store sales records in Excel format, which are then processed through stages starting from preprocessing to evaluating clustering results using the silhouette coefficient method to ensure clustering accuracy. The results of this study are expected to help stores in making decisions related to stock management, adjusting marketing strategies, and increasing customer satisfaction.