Although trip purpose inference based on passively collected data has long been investigated, less attention has been paid to inter-city trips. The reason is , except using ticket sales data, only limited trips can be extracted due to the lower frequency of inter-city trips during daily life. However, for ticket sales data, only limited features can be explored due to the lower spatial resolution of trajectories. Therefore, this paper endeavoured to exploit the potential of ticket sales data from the perspective of the group. Theoretically, by introducing concepts of text mining, the trip purpose of a group can be viewed as analogous to the topics of a document. Trip purpose was characterized by a time topic model (TTM) that incorporates start time, in contrast to latent Dirichlet allocation (LDA). This approach was implemented via a three-step method. First, groups were reconstructed from tickets. Second, three types of features, i.e., demographic, experience and co-travel network features, were extracted as a series of words to describe passengers. Third, trip purposes were automatically clustered based on the co-occurrence of words in the same group using a TTM. This paper presents comparison experiments to evaluate feature sets and the model performance based on a web -based travel survey, including the ground truth. Moreover, this paper highlights the practical use of a TTM to detect anomalies beyond anticipated trip purpose based on large-scale ticket sales data collected from Beijing, China. The full feature set was found to be preferable since both precision and recall increased when demographic and co-travel network features were considered. Meanwhile, the TTM produced robust and balanced predictions and exhibited additional power to recognize personal business compared with baseline methods.INDEX TERMS Inter-city trip, ticket sales data, topic model, trip purpose inference.