Klasterisasi Pola Penjualan Menu Makanan pada Rumah Makan menggunakan Metode K-Means Clustering

Abstrak

The culinary industry is one of the fastest-growing business sectors in Indonesia, as evidenced by the increasing number of restaurants emerging across the country. This intense competition demands that each restaurant develop effective strategies to attract customers and enhance profitability. One such strategy is analyzing menu sales patterns. This study contributes to the field of informatics, particularly in the application of data mining and machine learning techniques to support strategic decision-making in the culinary sector. The K-Means Clustering method was employed to analyze 12,404 daily sales transactions from a restaurant. The sales data were collected and analyzed to identify groups of menu items with similar sales characteristics. The research stages included data preparation, processing using RapidMiner and Microsoft Power BI, and analysis of the Clustering results. The quality of the clusters was evaluated using the Davies-Bouldin Index, which yielded a score of 0.354, indicating good separation and compactness between clusters. The analysis revealed that the optimal number of clusters is five, representing categories of highly popular, moderately popular, and less popular menu items. The most popular items include Chicken Rice, Tea, Catfish Rice, Chicken, and Potato Fritter. Meanwhile, the least preferred menu items include Minced Meat, Beef Tendon Rice, Jackfruit Curry, Beef Tendon, and Tempe. This Clustering provides valuable insights for restaurants to focus on developing popular menu items and consider improving or removing those that are less favored. The implementation of these Clustering results supports strategic decisions related to ingredient inventory management, menu promotion, and improvements in operational efficiency and customer satisfaction.