Satisfaction of customers is the most important factor for mobile operators to be successful. This needsrneffective customer segmentation and segment targeted mobile service packaging and delivery. Segmentationrndifferentiates customers into multiple groups that manifest different service needs and preferences, thusrndifferent service packages. It has been traditionally performed using demographic and value-basedrnsegmentation methods based on customer survey data. For improved efficiency, advanced clusteringrntechniques that exploit existing historical customer data from network management system have been applied.rnInstead of using a single dimension of value-based segmentation, the historical data set with many featuresrnwas applied to assess the customer service usage behavior from different dimensions. For a dataset with manyrnattributes, such advanced clustering techniques have not been investigated in the Ethiopian context. rnThe thesis work investigates and compares the performance of K-means and expectation-maximizationrnalgorithms for usage-based clustering using voice, SMS and internet service usage call detail record data ofrnmobile customers. The performance was compared using metrics such as cluster size or ratio, cluster cohesionrnor compactness and separation between centroid values. These metrics were used to evaluate the quality ofrnthe clustering result of the algorithms in identifying distinguished customer segments from each service usagerndataset for mobile service packaging purposes. Optimal cluster size per dataset was determined using elbowrnmethod. In the study, data processing and algorithm implementations were performed using WEKA datarnmining tool. rnAchieved results indicate that for all the datasets the EM algorithm formed compact clusters with low levelrnof within cluster variance. On the other hand, K-means clustering has a better quality in assigning instancesrnto each cluster fairly. In general, the study identified important additional attributes from the CDR datasetrnto differentiate customers for mobile service packaging purpose. These additional features enhance the insightrnon customers to provide well differentiated mobile service packages.