Chairun Nisak, Endang Sugiharti

Customer Lifetime Value Clustering Using K-Means Algorithm with Length Recency Frequency Monetary Model to Enhance Customer Relationship Management

Introduction

Customer lifetime value clustering using k-means algorithm with length recency frequency monetary model to enhance customer relationship management. Enhance CRM with Customer Lifetime Value (CLV) clustering via K-Means & LRFM. Identify low-value ("almost lost") and loyal customers for targeted retention strategies.

Abstract

The current era of business growth is fraught with challenges and competition due to rapid technological advancements, rapid market growth, and globalization. This research discusses customer management strategies to enhance Customer Relationship Management (CRM) at PT Digibook Sarana Promosi Indonesia, a company in the digital printing industry. With the emergence of numerous competitors in this challenging business growth era, the k-means algorithm and Length, Recency, Frequency, Monetary (LRFM) model are employed for customer clustering. The results identify two main customer groups. The first group falls into the category of almost lost or uncertain lost customers with the symbol L↓R↑F↓M↓, exhibiting low Customer Lifetime Value (CLV), suggesting a "let go" strategy to focus on more valuable customers. The second group comprises high-value loyal customers with the symbol L↑R↓F↑M↑, demonstrating high CLV, recommending an "enforced" strategy to maintain customer loyalty through loyalty programs. This research indicates that the optimal number of clusters is 2, validated using the ClValid method, with the best values on connectivity, Dunn index, and silhouette.

Full Text

Comments

You need to be logged in to post a comment.