Multi-factor Fusion POI Recommendation Model.

In the context of the rapid development of location-based social networks (LBSN), point of interest (POI) recommendation becomes an important service in LBSN. The POI recommendation service aims to recommend some new places that may be of interest to users, help users to better understand their cities, and improve users’ experience of the platform. Although the geographic influence, similarity of POIs, and user check-ins information have been used in the existing work recommended by POI, little existing work considered combing the aforementioned information. In this paper, we propose to make recommendations by combing user ratings with the above information. We model four types of information under a unified POI recommendation framework and this model is called extended user preference model based on matrix factorization, referred to as UPEMF. Experiments were conducted on two real world datasets, and the results show that the proposed method improves the accuracy of POI recommendations compared to other recent methods.