Methods, systems, and computer programs are presented for analyzing profiles and building profile models that can be used to personalize search results for a member on a social network. In example embodiments, a system aggregates data about members on the social network including member profile data, customer relation data, and member communication data. The system further extracts attribute values from the aggregated data and maps the attribute values onto attribute vectors on a social data map. Based on the mapping, the system determines a model member profile for the member. The system further generates candidate attribute vectors for search results from a search for the member and determines a similarity score between the model member profile and each candidate attribute vector. The system further ranks the search results based on the similarity score and presents a ranked display of the search results to the user.