Customer segmentation in e-commerce: K-means vs hierarchical clustering

Customer segmentation is important for e-commerce companies to understand and target different customers. The primary focus of this work is the application and comparison of K-means clustering and hierarchical clustering, unsupervised machine learning techniques, in customer segmentation for e-commerce platforms. Clustering leverages customer search behavior, reflecting brand preferences, and identifying distinct customer segments. The proposed work explores the K-means algorithm and hierarchical clustering. It uses them to classify customers in a standard e-commerce customer dataset, mainly focused on frequently searched brands. Both techniques are compared based on silhouette scores and cluster visualizations. K-means clustering yielded well-separated segments compared to hierarchical clustering. Then, using the K-means algorithm, customers are classified into different segments based on brand search patterns. Further, targeted marketing strategies are discussed for each segment. Results show three customer segments: high searchers-low buyers, loyal customers, and moderate engagers. The proposed work provides valuable insights into customers that could be used for developing targeted marketing campaigns, product recommendations, and customer engagement strategies to enhance the conversion rate, customer satisfaction, and, in turn, the growth of an e-commerce platform.