Friend recommendation algorithm based on location-based social networks

The rapid expansion of user data and geographic location data in the location-based social networking applications, it is become increasingly difficult for users to quickly and accurately find the information they need. The characteristics of the traditional friend recommendation algorithm are analyzed and discussed in this paper. In order to improve the performance of friend recommendation, we proposed a linear framework combines the three traditional friend recommendation algorithms, which are recommendation based on the proportion of common friends, recommendation based on user-based collaborative filtering and recommendation based on normal check-in location, respectively. Real dataset are used to verify our new method. The experimental results show that compared with the existing algorithms, our improved adaptive recommendation algorithm has better result, which can effectively improve the accuracy and recall rate of friend recommendation.