Many mobility prediction models have emerged over the past decade to predict a user’s next location through the utilisation of user trajectories. However, the performance is constrained by the quantity of user trajectory data. This research introduces a new approach by combining knowledge of individual travel behaviour and collective preferences of users sharing similar daily activity patterns. First, users are clustered into different groups by their daily activity profiles. Second, each group’s collective preferences (i.e. activity and travel distance preferences) are extracted. Then, individual travel behaviour and collective preferences are integrated for the next location prediction. A mobile phone dataset from Shanghai, China, is used for model validation. The results show that the proposed model achieves a prediction accuracy of over 80% during most of the day. Moreover, there is a maximum increase of 16% in prediction accuracy compared with baseline models when users are highly mobile.
- collective preferences
- distinct daily activity patterns
- Human mobility prediction
- mobile phone positioning data
- user clustering
ASJC Scopus subject areas