Research Article

Exploring for Route Preferences of Subway Passengers Using Smart Card and Train Log Data

Table 4

Travel route estimation result of the comparison models.

DivisionEstimated number of tripsEstimated choice probability (%)F1 score
Route 1Route 2Route 1Route 2

Actual14510857.342.7ā€”
GMM1648964.835.20.688
MRL13811554.545.50.739
PA1579662.137.90.918
Proposed15010359.340.70.963

GMM: Gaussian mixture model. MRL: maximum route length model. PA: parametric distribution model