In this paper we investigate the behavioral differ- ences between mobile phone customers with prepaid and postpaid subscriptions. Our study reveals that (a) postpaid customers are more active in terms of service usage and (b) there are strong structural correlations in the mobile phone call network as connections within customers of the same subscription type are much denser than those between the two types. Based on these observations we develop an efficient approach to detect the subscription type of customers by using information about their personal call statistics, and also their egocentric networks. The key of our approach is to cast the classification problem as a problem of graph labeling, which can be solved by max-flow min-cut algorithms. Our experiments show that, by using both user attributes and relationships, the proposed graph labeling approach is able to achieve a classification accuracy of 87%, which outperforms by 7% supervised learning methods using only user attributes.