Customer Segmentation in Online Retail Using K-Means Clustering Classification and Principal Component Biplot

In the online retail sector, comprehending customer behavior is the key to identifying essential patterns and trends that drive successful marketing strategies and customized product offers. The segmentation process divides groups into segments or subsets sharing attributes and characteristics which, in customer segmentation, help to classify and understand customer preferences, needs, and purchasing behaviors more deeply. Marketing techniques, machine learning, and statistical methods such as Cohort Analysis, Recency, Frequency, Monetary Value (RFM) analysis, K-means clustering, and Principal Component (PCA) Biplot, are implemented in this work to provide a suitable framework for effective customer segmentation. Cohort Analysis captures the customer lifecycle across segments, while RFM analysis categorizes behavioral customers by percentiles based on three RFM metrics. K-means refines clustering within segments using RFM attributes. PCA analysis visually simplifies complex relationships within customer groups, enhancing data understanding. Outcomes yield a robust framework. PCA and K-means reveal customer patterns, showing tendencies and interplay between Frequency and Monetary Value. Notably, K-means employs RFM data, and PCA uses the RFM dataset, enhancing segmentation coherence. This comprehensive approach provides insights to shape targeted strategies, enhancing marketing effectiveness and customer engagement.