The retail sector increasingly uses data mining approaches to identify customer purchasing behaviors and improve service quality. The Recency, Frequency, and Monetary (RFM) model, when integrated with machine learning, effectively segments customers and offers profound insights into their purchase behavior. While customer segmentation can be efficiently executed using the RFM model, the model is constrained to three factors and does not disclose segments based on demographic characteristics and purchase history. However, the influence of customer purchase attributes on marketing strategies is highly significant. This study implemented a cascaded solution integrating the RFM model with behavioral variables and conducted a comparative analysis of the Modified Fuzzy C-Means (MDFCM) and Crespo’s Dynamic Fuzzy C-Means (CDFCM) models. An experiment was conducted using a retail dataset and the results revealed the presence of two to four clusters exhibiting similar characteristics over a specified duration. The efficacy of the models is assessed using standard metrics such as Silhouette scores and the Xie-Beni index (XB-index). The evaluation indicated that the implemented cascaded RFM model yielded stable results with six clusters; however, it was observed to perform optimally with two clusters. Conversely, the MDFCM exhibited improved performance as the number of clusters increased, while the CDFCM demonstrated superior performance with two to three clusters, subsequently declining thereafter. Businesses can utilize this model to strategically analyze customers’ behavior through their purchasing history.