Up to now, we have presented a user agnostic network-based analysis of the recommendations. In this chapter we present a user-centric evaluation of the recommender algorithms. This user-based approach focuses on evaluating the user’s perceived quality and usefulness of the recommendations. The evaluation method considers not only the subset of items that the user has interacted with, but also the items outside the user’s profile. The recommender algorithm predicts recommendations to a particular user—taking into account her profile—and then the user provides feedback about the recommended items. Figure 7.1 depicts the approach.