<![CDATA[The Indonesian electronic retail industry is experiencing rapid growth along with digital transformation. However, available sales data is often only stored as transaction records without further analysis, so it has not been optimally utilized for marketing decision making or customer segmentation. This study aims to implement the RapidMiner-based K-Means Clustering algorithm to analyze segmentation patterns of electronic products at XYZ Store. The dataset used includes the variables Transaction_ID, Product_ID, Product_Name, Category, Quantity, Unit_Price, Revenue, and Recency. The research stages include data collection, preprocessing (filtering, aggregation, and Z-Score normalization), K-Means application, and interpretation of clustering results. Determination of the number of clusters in this study uses the Elbow Method, which shows an optimal point at K = 3, so that number of clusters is chosen for the data grouping process. Based on the results of the application of the K-Means algorithm with the three clusters, the following are obtained: (1) Cluster 0 (High Sales & High Revenue) consisting of Smartphones, Laptops, and Tablets as superior products with a contribution of almost 60% of total revenue; (2) Cluster 1 (Medium Sales & Moderate Revenue) includes Televisions, Refrigerators, and Smartwatches with a stable contribution of around 27%; and (3) Cluster 2 (Low Sales & Low Revenue) contains Washing Machines, Speakers, Headphones, and Printers with a low contribution of only 14%. These findings provide a strategic basis for management in making business decisions, such as procurement priorities, seasonal promotions, product bundling, and clearance strategies. This study proves that the application of data mining with K-Means Clustering is effective in increasing operational efficiency and supporting the competitiveness of the electronics retail business in Indonesia.]]>
Copyrights © 2025
