Trip Purpose Inference and Spatio-Temporal Characterization Based on Anonymized Trip Data: Empirical Study from Dockless Shared Bicycle Dataset in Xi’an, China

The rapid and widespread deployment and applications of the Internet of Things (IoT) and big data technology has generated massive personal travel data. Although most of the data are anonymized, they still provide possibilities for analyzing individual travel behavior. It is worthwhile to explore how to more accurately infer travel purposes based on trajectory data, smart card fare data, or shared bicycle data. In this paper, an improved research framework is proposed for travel purpose inference by applying the gravity model, Bayesian criterion, and spatial clustering method. The gravity model and Bayesian rule are used to calculate the probability of users traveling to nearby POIs (points of interest), and the clustering algorithm is used to identify the locations regularly visited by users. Through the identification of maximum probability POI and regular trips, different travel purposes represented by POI can be distinguished. The results showed that the identification of regular trips could verify and complement the recognition of trip purposes by POIs. Using Xi’an city of China as an example for the study, the results show that: 1) regular trips accounted for 32% of the week’s trips; 2) there are 10% of the trips reflect different trip purposes for the same POI; 3) it is also important to note that 70% of the users have a parking error of fewer than 100 m when going to the exact location. This distance can provide a reference for the study of bicycle commuting. Finally, we analyzed the spatial and temporal distribution characteristics of different trip purposes. The analysis of the spatial and temporal distribution can provide suggestions for the operation of bike-sharing enterprises and the management of regulators.