CRM departments regularly apply data mining methods to predict customer behavior. These methods typically ignore the position of the customer in a social network. Many companies do not only have data about individual customer behavior, but also about the social network of customers. The telecommunication industry is an area , where companies accumulate huge amounts of telephone calling records providing information not only about the usage behavior of a single customer, but also about how customers interact with each other. The goal of this thesis is to leverage network data for marketing applications. Two topics are considered: First, it is analysed how predictive accuracy of classification tasks can be improved by leveraging finformation about the social network of a customer Second, different centrality measures for viral marketing are investigated. Viral marketing refers to marketing techniques that seek to exploit pre-existing social networks to produce exponential increases in brand awareness, through viral processes similar to the spread of an epidemic. In case data about tthe customer network is available, centrality measures can be used to spread viral marketing campaigns in a social network. The literature on network theory describes a large number of such centrality measures. In this thesis, we use computational experiments to compare different centrality measures for the diffusion of marketing messages. We found a significant lift when using central customers in message diffusion, but also found significant differences in the various centrality measures depending on the underlying network topology and diffusion process.