K-Means clustering interpretation using recency, frequency, and monetary factor for retail customers segmentation

K-Means clustering interpretation using recency, frequency, and monetary factor for retail customers segmentation

Customer segmentation
Industrial and innovation
K-Means algorithm
Machine learning
Recency, frequency, and monetary analysis
Small and medium enterprises

Efforts to retain customers represent a crucial customer relationship management (CRM) strategy in every business, offering the potential to enhance profits, particularly for small and medium enterprises (SMEs). In the context of this study, which focuses on the transaction dataset of retailers in a developing market, Indonesia, the emphasis has predominantly been on customer attraction rather than the implementation of customer retention strategies. The primary objective of this research was to scrutinize customer transaction data within the dataset. The K-Means clustering (KMC) method, integrated with recency, frequency, and monetary (RFM) attributes, was employed to classify customers and formulate effective strategies for customer retention. Conducted through a descriptive research method with a quantitative approach, the study involved sequential stages of data preprocessing and RFM analysis for comprehensive data analysis. The outcomes revealed the identification of 5 distinct clusters with associated strategies based on the RFM scores obtained. These strategies, tailored to each cluster, serve as valuable insights in industrial and innovation for marketing and business strategic teams, offering practical approaches to customer retention that can lead to increased benefits for SMEs.

Agung Nugraha1, Yutika Amelia Effendi2, Nicholas1, Zejin Tao1, Mokh Afifuddin3, Nania Nuzulita4

Journal homepage: http://telkomnika.uad.ac.id

Jan 23, 2025

PERI IRAWAN

PDF

ENGLISH

TEXT