Integrating geographical and temporal influences into location recommendation: a method based on check-ins

In the online-to-offline (O2O) business model, location recommendation plays an important role and is an essential component of the location-based services. The check-in data, which contains both the geographical and temporal information, has been treated as an important data source for location recommendation. Location-based collaborative filtering is a popular technique for computing location similarities to arrive at the recommendation. In this research we analyze the geographical and temporal characteristics of the user’s check-in activity and incorporate it for deriving recommendations using location-based collaborative filtering. To model the geographical proximity between the recommended location and the visited location, we first get the user’s active regions using the multiple-center discovering algorithm; we then derive the probability of visiting the unvisited locations by using the power-law distribution on the distance. The geographical proximity is derived by multiplying the visiting probability and the check-in ratio of the active region. To consider temporal information, we propose the concept of time-aware location similarity, which splits the user check-ins into twenty-four different time slots in a day. To address the sparsity problem created by splitting check-in data, we propose a mechanism to measure the similarities between time slots and use these similarities to infer the empty ratings. The geographical proximity and time-aware location similarity are integrated to generate the location similarity. We perform the experiments to verify the effectiveness of the proposed algorithm. The experimental results show the superiority of our method compared with the benchmarks.