Search for: All records

We introduce a novel check-in time prediction problem. The goal is to predict the time a user will check-in to a given location. We formulate check-in prediction as a survival analysis problem and propose a Recurrent-Censored Regression (RCR) model. We address the key challenge of check-in data scarcity, which is due to the uneven distribution of check-ins among users/locations. Our idea is to enrich the check-in data with potential visitors, i.e., users who have not visited the location before but are likely to do so. RCR uses recurrent neural network to learn latent representations from historical check-ins of both actual and potential visitors, which is then incorporated with censored regression to make predictions. Experiments show RCR outperforms state-of-the-art event time prediction techniques on real-world datasets. 

It is long known that a user's mobility pattern can be affected by his social connections. Users tend to visit same locations visited by their friends. In this paper we investigate the inverse problem: How does a set of user trajectories reflect their social connections. To this end, we define the social connection prediction problem. Given two users, predict the probability that they are friends by mining their historical trajectories. A first approach to do so is to exam how often the two users visit the same location at the same time, which suffers from the problem that different locations/times may have different predictive power. We propose a comprehensive prediction model that is able to capture this difference between locations and time slots. To demonstrate its effectiveness, we trained the proposed model using the publicly available Foursquare dataset. The result shows the proposed model is able to predict existence of social connections between randomly selected users significantly more accurate comparing with the naive method.