Exploring Bikesharing Travel Patterns and Trip Purposes Using Smart Card Data and Online Point of Interests

Abstract

The primary objective of this study was to investigate the bikesharing travel patterns and trip purposes by combining smart card data and online point of interests (POIs). A large-scale smart card trip data was collected from the bikesharing system in New York City. The POIs surrounding each station were obtained from Google Places API. K-means clustering analysis was first applied to divide bikesharing stations into five types based on their surrounding POIs. The Latent Dirichlet Allocation (LDA) analysis was then conducted to discover the hidden bikesharing travel patterns and trip purposes using the identified station types and smart card data. The performance of the LDA models with and without POI data was compared to identify whether the POI data should be used. Finally, a practical application of the proposed methods in bikesharing planning and operation was discussed. The result of comparative analyses verified the importance of POI data in exploring bikesharing travel patterns and trip purposes. The results of LDA model showed that the most prevalent travel purpose in New York City is taking public bike for eating, followed by shopping and transferring to other public transit systems. In addition, the result also suggested that people living around the bikesharing stations are more likely to transfer to other commuting tools on the morning peak and ride for home after work. The proposed methods can be used to provide useful guidance and suggestions for transportation agency to develop strategies and regulation that aim at improving the operations of bikesharing systems.