Application of K-Means for Clustering Analysis of Moring Sales in Stores Meowring

Abstract

The complexity of stock management and marketing strategy at Toko Meowring requires a systematic analytical approach. This study implements the K-Means algorithm with a Knowledge Discovery in Databases (KDD) approach to optimize product segmentation. The analysis was conducted on 246 sales data over a year, considering product type, spiciness level, and sales volume. Evaluation using Davies-Bouldin Index (DBI) resulted in 7 optimal clusters with a DBI value of 0.402. The formed clusters identified bestseller product groups dominated by original flavors, low-demand products, moderate popularity products, stable sales products, and unique products with limited demand. This clustering enables optimization of inventory management, development of targeted promotional strategies, and improvement of product layout. The results validate the effectiveness of the K-Means algorithm in enhancing product segmentation accuracy for strategic decision-making.