Point-of-Interest (POI) recommendation is an important service in location-based social networks (LBSNs) since it can help a user to discover new POIs for future visiting. In order to provide better recommendation experience, a novel POI recommendation paradigm, named successive POI recommendation, has been proposed. The difference between traditional POI recommendation and successive POI recommendation is that successive POI recommendation focuses on recommending POIs that the target user may like to visit within a time period (e.g., a few hours). To address this problem, we propose a new graph-based latent representation model called GLR, to obtain the latent vectors of temporal successive transition influence and temporal user preference based on the historical check-in records. We also propose a novel method named GLR_GT to employ these latent vectors and geographical influence of POIs to perform successive POI recommendation. Moreover, we also propose an extended method named GLR_GT_LSTM to employ a long short-term memory (LSTM) neural network to model users’ complex transition behavior. Several experiments are conducted on some real-world LBSN datasets. Experimental results show that our proposed method GLR_GT_LSTM outperforms the other prior successive POI recommendation methods in terms of precision and recall.