Segmentation of Mobile User Groups Based on Traffic Usage and Mobility Patterns

For the purpose of precision marketing, this paper aims to identify 2G user groups that are most likely to immigrate to 3G/4G mobile communication networks. Two dimensions of user behaviors are considered important for our purpose: traffic usage and mobility. User-labeled raw data is first extracted from the Gn interface. Such raw data is further processed to map each user into a probabilistic vector space, which characterizes the time-varying traffic usage and mobility patterns of the user. A K-Means clustering algorithm with Canopy approach is subsequently applied to the normalized vector space data for user group segmentation. The results indicate that the proposed method can be helpful for mobile operators to target valuable potential user groups in business promotion.