RFM-Based Customer Segmentation Using K-Means Clustering to Recommend Marketing Strategies for Motorcycle Repair Shops

Abstract

Motorcycle repair workshops, as service-based businesses, require an understanding of customer characteristics to develop more effective marketing strategies. However, differences in customer transaction behavior make generalized marketing strategies less effective in meeting the needs of different customer groups. Customer segmentation is an approach that enables businesses to classify customers based on their transaction characteristics, allowing the identification of valuable customers and the development of more targeted marketing strategies. This study aims to apply the Recency, Frequency, Monetary (RFM) method and the K-Means Clustering algorithm to segment customers of AHASS Cimalaka Sumedang Motorcycle Workshop. The resulting customer segments are expected to support the formulation of marketing strategy recommendations, improve customer loyalty, and facilitate more effective marketing decision-making. Differences in customer transaction behavior reduce the effectiveness of generalized marketing strategies, highlighting the need for customer segmentation based on transaction data. To apply the Recency, Frequency, Monetary (RFM) method and the K-Means Clustering algorithm for customer segmentation and to develop marketing strategy recommendations. This study employed a quantitative approach consisting of data preprocessing, RFM calculation, data normalization, K-Means clustering, and cluster evaluation. The proposed approach successfully segmented customers into five clusters based on their RFM characteristics, namely Potential Loyal Customer, At Risk Customer, Lost Customer, Inactive Customer, and Loyal Customer, which served as the basis for prioritizing targeted marketing strategies. The combination of the RFM method and the K-Means Clustering algorithm effectively supports customer segmentation and provides a reliable basis for developing more targeted and effective marketing strategies.