Like many other transit modes, the metro provides stop-to-stop services rather than door-to-door services, so its use undeniably involves first- and last-mile issues. Understanding the determinants of the first- and last-mile mode choice is essential. Existing literature, however, mostly overlooks the mode choice effects of traffic safety perception and attitudes toward the mode. To this end, based on a face-to-face questionnaire survey in Shenzhen, China, this study uses the two-sample t-test to confirm the systematic differences in traffic safety perception and attitudes between different subgroups and develops a series of multinomial logistic (MNL) models to identify the determinants of first- and last-mile mode choice for metro commuters. The results of this study show that: (1) Walking is the most frequently used travel mode, followed by dockless bike-sharing (DBS) and buses; (2) Variances in traffic safety perception and attitude exist across gender and location; (3) Vehicle-related crash risks discourage metro commuters from walking to/from the metro station but encourage them to use DBS and buses as feeder modes; (4) DBS–metro integration is encouraged by the attitude that DBS is quicker than buses and walking, and positive attitudes toward the bus and DBS availability are decisive for the bus–metro and DBS–metro integration, respectively; and (5) Substantial differences exist in the mode choice effects of traffic safety perception and attitudes for access and egress trips. This study provides a valuable reference for metro commuters’ first- and last-mile travel mode choice, contributing to developing a sustainable urban transport system.

Transit offers stop-to-stop services rather than door-to-door services. The trip from a transit hub to the final destination is often entitled as the “last-mile” trip. This study innovatively proposes a hybrid approach by combining the data mining technique and multiple attribute decision making to identify the optimal travel mode for last-mile, in which the data mining technique is applied in order to objectively determine the weights. Four last-mile travel modes, including walking, bike-sharing, community bus, and on-demand ride-sharing service, are ranked based upon three evaluation criteria: travel time, monetary cost, and environmental performance. The selection of last-mile trip modes in Chengdu, China, is taken as a typical case example, to demonstrate the application of the proposed approach. Results show that the optimal travel mode highly varies by the distance of the “last-mile” and that bike-sharing serves as the optimal travel mode if the last-mile distance is no more than 3 km, whilst the community bus becomes the optimal mode if the distance equals 4 and 5 km. It is expected that this study offers an evidence-based approach to help select the reasonable last-mile travel mode and provides insights into developing a sustainable urban transport system.