This project focuses on evaluating named group recommendation algorithms and analyzing the recommendation output. Our approach is developing a Facebook-based testbed for evaluating how the recommendation can reduce user’s effort to create friend-lists and visually validating the recommendation results. The testbed has three components: a recommendation engine, a friend-list editor, and a tool for visualizing recommendations. The recommendation engine implemented in Facebook mines social graphs to make predictions on friend-lists. The Friend-list Editor allows editing recommendations and measures the efforts a user takes to create friend-lists with and without recommendations. The visualization tool provides a set of visualization methods of social graphs and friend-lists.