In today’s competitive landscape, customer centric strategies are the key to sustainable growth. This work focuses on the power of Recency, Frequency and Monetary (RFM) analysis combined with various clustering techniques to transform the customer segmentation in the automobile parts sector. The dataset used in this work is the sales data of automobile parts manufacturing section for three years. Initially, RFM analysis is performed on the dataset and the customers are grouped into three different categories. To further enhance the customer segmentation and profiling, the RFM score computed from the data are fed to four clustering algorithms K-means, BIRCH, agglomerative and spectral. The proposed method is evaluated on the performance measures, Silhouette score, Davies-Bouldin Index and Calinski-Harabasz Index. Experimental results demonstrated the highest intracluster compactness and intercluster distance with a Silhouette score of 0.50 using spectral clustering technique. Spectral clustering is suited well for nonlinear relationships, and it handles overlapping segments effectively. Four distinct customer personas have been identified with varying Recency, Frequency and Monetary patterns. The results reveal the way the data-driven segmentation can uncover actionable insights, enabling personalized marketing strategies and retention programs.