Segmentasi Pelanggan Berbasis RFMT Menggunakan K-Means dan Hierarchical Clustering

Abstract

The rapid growth of online retail has generated vast transactional data, creating significant opportunities for advanced customer segmentation. While the standard RFM (Recency, Frequency, Monetary) model is widely used in Customer Relationship Management (CRM), it possesses a key limitation by not capturing the temporal dynamics between customer purchases. This research addresses that gap by proposing an RFM-T model, which enhances the traditional framework with Interpurchase Time (IPT) to provide a more holistic view of customer behavior. Using a dual-clustering methodology on an online retail dataset, the K-Means algorithm is first applied for broad segmentation, followed by Hierarchical Clustering to explore deeper sub-segments within high-value groups. The process yielded four primary clusters, and the model's robustness was systematically validated through a strong Silhouette Score, a low Davies-Bouldin Index, and a high Calinski-Harabasz Index. This detailed analysis successfully identified distinct customer personas, such as 'Consistent Loyalists' (low IPT) and 'Periodic Premium Buyers' (high monetary value), which are crucial for developing targeted strategies. The findings demonstrate that this integrated RFM-T framework provides a quantitatively validated with Silhouette Score 0.410, Davies-Bouldin Index 0.720, and Calinski-Harabasz Index 1365.14 this score show actionable model for personalized marketing and effective customer retention.