K-Means Clustering Method For Customer Segmentation Based On Potential Purchases

Abstract

The rapid growth in customer data has driven companies to develop smarter and more effective marketing strategies. One efficient approach is customer segmentation, which involves dividing a market or group of customers into smaller segments based on similar characteristics or behaviors. Customer segmentation improves understanding of customer needs, preferences, and behavior. This study uses customer segmentation based on purchase potential at Fast Moving Consumer Goods (FMCG). Analyzing potential purchases can help identify market opportunities, implement more effective pricing, target promotions, manage stock and distribution, and develop new products to enhance customer satisfaction. The most commonly used segmentation method is the K-Means Clustering algorithm, which groups data into homogeneous clusters. This study aims to segment customers based on potential purchases using the K-Means Clustering method. The customer dataset in FMCG stores was divided into three clusters using seven attributes: Sex, Marital Status, Age, Education, Income, Occupation, and Settlement Size. The results, calculated in Microsoft Excel, concluded after four iterations with three clusters: k1 (Cluster 1) with 535 customers having low purchase potential, k2 (Cluster 2) with 685 customers having high purchase potential, and k3 (Cluster 3) with 7810 customers having medium purchase potential.