The task of points-of-interest recommendation has become an essential feature in social networks (LBSN) with the significant growth of shared data on LBSN. However it remains a challenging problem, because of the high level of sparsity of the data in LBSN. Moreover, in this context the mobility behavior of the users is very heterogeneous, ranging from urban to worldwide mobility. In this paper, we explore the impact of spatial clustering on the recommendation quality. The proposed approach combines spatial clustering with users' influences. It is based on a Poisson factorization model built on an implicit social network, inferred from the geographical mobility patterns. We conduct a comprehensive performance evaluation of our approach on the YFCC dataset (a very large-scale real-world dataset). The experiments show that our approach achieves a significantly superior quality compared to other existing recommendation techniques.