Method, apparatus, and a computer-readable storage device for determining similarities. A plurality of sets having social network service members as entities is constructed by associating each of the social network service members with each of a predetermined selection of professional outcomes by school of graduation of the member. One of the plurality of sets is selected. A similarity algorithm calculates the similarity score of at least some of the plurality of sets in the plurality of sets to the selected one of the plurality of sets, and presents for rendering the k sets in the plurality of sets with the highest similarity scores. The similarity algorithm used may be a cosine similarity algorithm using the sets as vectors.