A complementing preference based method for location recommendation with cellular data.

Location recommendation in a city district plays an essential role for people city experience. Most existing studies consider user mobility data as implicit feedback, and adopt collaborative filtering frameworks to make recommendations. However, most of them treat all unvisited locations as negative examples. This method fails to provide details about users preferences, such as graded ratings in explicit feedback. To cope with this problem, we define geographically similar friends, and propose a Complementing Preference Based Collaborative Filtering method (CPBCF). Specifically, we first build a geosimilarity network for a user and identify the possible locations that he or she could visit. Limiting the study to just these locations alleviates data sparsity caused by a huge number of unrelated locations. Then, we complement the user–location preference matrix using the information from geographically similar friends and adopt a weighted regularized matrix factorization model to make recommendations. We evaluate our method on real-world dataset and the experimental results demonstrate the effectiveness of our methods. • Complement user's preference to cope with incomplete user preference information in location recommendation. • Verify the feasibility of complementing user's preferences with geographically similar friends' locations. • Propose a method to complement the user–location preference matrix, considering personalization. • The experimental results show the effectiveness of the work. [ABSTRACT FROM AUTHOR]