The customer lifetime value (CLV) metric aims to predict the importance level of each customer, offering to companies the ability to group them into homogenous segments, to propose appropriate marketing actions and to optimize resource allocation. CLV is widely suggested as a new base to segment customers. To succeed the CLV based segmentation, companies need to use the appropriate CLV model which allows predicting with accuracy the customer behavior, especially the customer lifetime and the number of transactions. The Pareto/NBD and the BG/NBD are the most relevant CLV models, assuming that the number of transactions made by each customer follows a Poisson process. However, many real data violate the assumption of equi-dispersion that underlies the Poisson distribution. The BG/GCP model retains the same BG/NBD assumptions while modeling customer lifetime. However, it considers that the number of trans-actions follows a Conway–Maxwell–Poisson (CMP) distribution which is a two parameter generalization of the Poisson offering more flexibility in modeling dis-crete data. In this paper we propose to compare segmentation performance of the BG/GCP compared to the Pareto/NBD and the BG/NBD models, and to select the most efficient one. This performance is evaluated using three different clustering methods namely K-means, Fuzzy c-means and EM Clustering. Using two simulat-ed datasets, presenting respectively an over and an under dispersion from Poisson distribution, the empirical analysis shows that the BG/GCP model based on CMP flexibility offers the best segmentation performance.