| Abstrak/Abstract |
Database marketing has gained significant importance in today's business landscape due to the availability of vast customer data held by many companies. This has led to the widespread adoption of database marketing across various industries, such as retail, e-commerce, banking, and telecommunications. Continuously understanding customer behavior is crucial as their trends and preferences evolve over time. This study aims to support companies in enhancing customer loyalty, retention, and fostering long-term relationships by better understanding their customers. To achieve this, companies can monitor customer behavior and adjust their marketing strategies, one effective approach being the utilization of Recency, Frequency, and Monetary (RFM) analysis. RFM analysis, which stands for Recency, Frequency, and Monetary, is a technique used to segment customers based on their past purchasing behavior. Recency assesses how recently a customer has made a purchase, Frequency measures the frequency of a customer's purchases, and Monetary evaluates the amount a customer spends per purchase. In this study, the K-Means unsupervised learning algorithm is employed to categorize customers into three groups: Loyal, Promising, and Need Attention based on Recency, Frequency, and Monetary features. The experimental findings indicate that the K-Means algorithm outperforms K-Medoids for customer segmentation, as evidenced by higher values for the Silhouette Coefficient (0.74), Davies Bouldin Index (0.51), and Calinski Harabasz Index (8972.97). To facilitate the interpretation of these results, a web dashboard was created using the Streamlit Python library. By visualizing the analysis outcomes through this platform, companies can gain valuable insights into customer behavior and preferences. |
