Understanding users’ patterns of visiting various location categories can help online platforms improve content personalization and user experiences. Current literature on predicting future location categories employs features that can be traced back to the users, such as spatial coordinates and demographic identities. Moreover, existing approaches typically suffer from cold start and generalization problems, and often cannot specify when the location category will be visited in the future. However, in a large social platform, it is desirable for models to avoid using user-identifiable data, and to generalize to unseen and new users. In this work, we construct a neural model, LocHabits, that omits user-identifiable inputs, leverages temporal and sequential regularities in the location category histories of Snapchat users and their friends, and predicts the users’ next-hour location categories. We evaluate our model on several real-life, large-scale datasets from Snapchat and FourSquare, and find that the model can outperform baselines by 14.94% accuracy. We confirm that the model can (1) generalize to unseen users from different areas and times, and (2) fall back on collective trends in the cold-start scenario. We also study the relative contributions of various factors in predicting future categories, and find that the users’ visitation preferences and most-recent visitation sequences play more important roles than time contexts, same-hour sequences, and social influence features.