Research Article

A Trip Purpose-Based Data-Driven Alighting Station Choice Model Using Transit Smart Card Data

Table 5

Results for alighting station estimation based on selected MNL and mixed logit models.

Trip purposeMNLMixed logit
ModelPercentageModelPercentage

HomeTwo factors (WT and IVT)66.30%ā€”ā€”
WorkTwo factors (WT and IVT)78.27%Three-factor utility function, WT distribution81.31%
OthersTwo factors (WT and IVT)70.74%75.35%
TotalTwo factors (WT and IVT)72.59%Three-factor utility function, independent distributions WT and TF79.23%