Agung Yuliyanto Nugroho
The garment industry faces challenges in grouping diverse goods based on their characteristics, which can affect the efficiency of the production process and inventory management. This study aims to apply the K-Means Clustering algorithm in garment goods classification to improve business process management and optimization. The K-Means algorithm, as one of the popular clustering methods, is used to group garment goods data based on features such as size, color, fabric type, and product model. This method begins with the selection of relevant features from the dataset obtained from the garment industry. Furthermore, the K-Means algorithm is implemented to determine the optimal number of clusters using the elbow score and silhouette methods. The clustering results are analyzed to evaluate the extent to which the algorithm can form homogeneous and business-relevant groups of goods. The results of this study indicate that the K-Means Clustering algorithm is effective in grouping garment goods into several categories that are consistent with business patterns and needs. The application of this method results in a better understanding of goods grouping that can improve production efficiency and facilitate inventory management. This study contributes to the best practices in the use of the K-Means algorithm in the convection sector and shows the potential of this method in supporting data-driven decision making. Keywords:,