In this paper, we propose a data mining framework that utilizes the concept of social network for the targeted advertising of products. This approach discovers the cohesive subgroups from customer?s social network which is derived from customer?s interaction data. Based on the set of cohesive subgroups, we infer the probabilities of customer?s liking a product category from transaction records. Utilizing such information, we construct a targeted advertising system. We evaluate the proposed approach by using real email logs and library-circulation data. The experimental results show that our approach yields better quality of advertisement.