Telecommunication companies use data mining techniques to maintain good relationships with their existing customers, attract new customers, and identify profitable/unprofitable customers. Clustering leads to a better understanding of customers and its results can be used for definition and decision-making for promotional schemes. In this research work, we use the 999-customer purchase records in the South Khorasan Telecommunication Company collected during a year. The purpose of this work is to classify customers into several clusters. Since the clusters and the number of their members are determined, the high-consumption users will be logged out of the system and the high-value customers who have been missed will be identified. We divide the customers into five categories: loyal, potential, new, missed, and high-consumption using the Clementine software, developing the RFM model to the LRFM model and the Two_Step and K_Means algorithms. Thus this category will be a good benchmark for a company's future decisions, and we can make better decisions for each group of customers in the future.