The popularity of location-based social networks (LBSNs) has led to an enormous amount of user-based check-in data.Recommended Points of Interest (POIs) plays a key role in meeting the needs of LBSN users. While recent work has explored the thought of adopting a collaborative ranking (CR) for recommendations, few attempts are made to include time-based information for POI recommendations using CR. In this article, we propose a two-phase CR algorithm that comes with the geographical influence of

more »

... POIs and is regularized supported the variance of recognition of POIs and user activities over time.Time-sensitive regularized penalizes users and POIs that have been more time-sensitive in the past, helping the model to account for long-term behavioural patterns while learning from user-POI interactions. Moreover, in the first phase, it attempts to rank the visited POIs higher than the unvisited ones and, at the same time, to apply the geographical influence. In the second phase, our algorithm attempts to rank the preferred POI users higher on the recommendation list. Both phases use a collaborative learning strategy that enables the model to capture complex latent associations from two different perspectives. Real-world dataset experiments show that our proposed time-sensitive collaborative ranking model beats the state-of -the-art POI recommendation methods.