E-commerce growth has led to vast amounts of customer data, making effective customer segmentation crucial for personalized marketing and customer relationship management. This paper presents a comparative study of unsupervised clustering algorithms for segmenting e-commerce customers based on RFM (Recency, Frequency, Monetary) attributes and additional behavioural factors such as customer satisfaction and tenure. We evaluate multiple clustering techniques – including K-Means, hierarchical clustering, and DBSCAN – to identify which algorithm yields the most coherent and well-separated customer groups. Cluster validity is assessed using internal metrics, notably the silhouette coefficient and the Davies-Bouldin index, to determine the optimal number of clusters and the quality of results for each method. Experimental results on real e-commerce data show that the choice of clustering algorithm significantly impacts segment formation. K-Means clustering achieved the highest silhouette score and lowest Davies-Bouldin index, indicating the best overall performance in capturing distinct customer segments. A detailed profile analysis of the resulting clusters reveals interpretable segments (e.g., high-value loyal customers, at-risk customers, new customers) with apparent differences in purchasing behaviour, satisfaction levels, and customer tenure. These findings provide insights into the strengths of different clustering approaches for customer segmentation and offer practical guidance for e-commerce firms to enhance customer targeting and retention strategies.