<![CDATA[Customer segmentation is a strategic approach in data-driven marketing, allowing businesses to identify purchasing patterns to enhance the effectiveness of marketing campaigns. This study implements the K-Medoids algorithm to analyze customer behavior based on transaction data to form more accurate customer clusters. The data used was obtained from transaction history and underwent preprocessing steps such as cleaning and normalization. The clustering process was conducted by determining the optimal number of clusters using the Elbow Method and evaluated with the Silhouette Score. The results indicate that the optimal number of clusters is two, with a Silhouette Score of 0.5602, demonstrating well-separated clusters. Based on the clustering results, marketing strategies can be optimized by adjusting loyalty programs and providing personalized product recommendations to enhance customer engagement. With this approach, businesses can improve customer satisfaction and the efficiency of data-driven marketing. Keywords: K-Medoids, Clustering, Customer Segmentation, Marketing Strategy]]>
Copyrights © 2025
