Unravelling commuters' modal splitting behaviour in mass transportation service operation

Document Type

Journal Article

Publication Date


Subject Area

mode - subway/metro, mode - bike, place - asia, place - urban, policy - sustainable, operations - frequency, economics - pricing, ridership - behaviour, ridership - commuting


Bike-sharing, Data mining, K-means, Mode choice, RFM model


One important factor in determining whether commuters will use public transport is spatial accessibility rooted in the first-mile problem. This study explores commuter behaviour in terms of how they utilize bike-sharing to manage the first-mile accessibility of a public transportation station. Historical data from Taipei Metro smart cards were analyzed using RFM (recency, frequency, and monetary) segmentation models to identify commuter segments. This study reveals two significant findings: comprehensive spatiotemporal characteristics and homogeneous behavioural patterns are derived from clustering algorithms. The city's penetration pricing strategy for bike-sharing motivates modal splitting transfer between bike-sharing and transit (MSTBT). In addition, we observed a supplementary and utilitarian relationship between bike-sharing and the metro. A convenient transportation network improves first-mile accessibility, thus the frequency of MSTBT usage is a key metric for measuring engagement. The findings provide a useful reference for urban planners promoting the design and development of sustainable transportation systems.


Permission to publish the abstract has been given by SpringerLink, copyright remains with them.