<![CDATA[The development of the gadget accessories retail industry demands adaptive marketing strategies to understand consumer behavior patterns more effectively. The main problem faced is the difficulty in grouping customers based on the characteristics of diverse purchasing behaviors. To overcome this, this study aims to implement the K-Means Clustering algorithm in intelligent systems to group customer data of gadget accessories into several groups that have similar purchasing patterns. The K-Means algorithm is used because of its ability to detect patterns and segment based on the similarity of customer attributes through an iterative process until convergence is achieved. The results of the study show that this method has succeeded in forming three main clusters, namely high-value customers with a high purchase frequency and dominance of premium products (C1), customers with low activity who require a special promotional approach (C2), and potential customers with medium activity who have the potential to increase their loyalty (C3). The results of this segmentation prove that the K-Means algorithm is effective in analyzing consumer behavior and can be the basis for data-driven decision-making for a more efficient marketing strategy and product recommendation system in the gadget accessories retail sector.]]>
Copyrights © 2025
