Metro stations’ passenger volumes are important parameters for planning and design. In this paper, a random forest regression model is proposed to predict the inbound/outbound passenger volume and the total passenger volume of each station during the workday, based on the Metro AFC data and POI data of Shanghai, China. The dependent variables include the inbound/outbound and total passenger volumes of each metro station, and the independent variables include the relative proportion of 15 types of POI data. The results show that the R-square values of the inbound and total volumes is 0.94, and the outbound volume is 0.95. The average relative error of the model (≈20%) indicates that its prediction accuracy is good. Moreover, the variable importance method based on permutation was used to analyze the factors affecting the passenger volumes of stations. This study’s findings are useful for metro station planning and design, and metro operation organization.
Predicting Passenger Volumes of Metro Stations Based on Random Forest Regression
22nd COTA International Conference of Transportation Professionals ; 2022 ; Changsha, Hunan Province, China
CICTP 2022 ; 2724-2731
2022-09-08
Conference paper
Electronic Resource
English
Improvements to passenger environment at metro stations and on trains
British Library Conference Proceedings | 1993
|Metro Timetabling for Time-Varying Passenger Demand and Congestion at Stations
DOAJ | 2018
|Dynamic Metro Stations Importance Evaluation Based on Network Topology and Real-Time Passenger Flows
Springer Verlag | 2023
|