Myfriend: A User Preference Based Friend Recommendation System for Social Networks

Existing social networking services recommend friends to users based on their social graphs, which may not be the most appropriate to reflect a user's preferences on friend selection in real life. Myfriend is a novel friend recommendation system for social networks, which recommends friends to users based on their life styles and preferences instead of social graphs. By taking advantage of sensor rich smart phones, Myfriend discovers life styles of users from user-centric sensor data, measures the similarity of life styles between users, and recommends friends to users if their life styles have high similarity. Upon receiving a request, Myfriend returns a list of people with highest recommendation scores to the query user. User can be able to given the user preferences and location preferences to improve the friend recommendation. Finally, Myfriend integrates a feedback mechanism to further improve the recommendation accuracy.