Cold-start recommendation strategy based on social graphs

Generally speaking, information filtering systems recommend users items that are related to their usage and/or static profiles or items visited or liked by users having same interests or habits. However, a new user who starts with an empty profile and who does not belong yet to any community could not benefit from this recommendation service. This problem is known as the cold start of a new user. In this paper, we propose an approach to overcome this problem by identifying key users within a social network as a result of the recommendation. It identifies the best entry points into the network to explore its content in terms of shared resources. The approach is based on an importance measure which combines several aspects characterizing the individuals within the social network. Preliminary results showed the effectiveness of our approach to tackle the cold-start problem.