Passenger Flow Forecasting using Support Vector Regression for Rail Transit

Bin Xia, Fanyu Kong, Songyuan Xie


Support vector regression is a promising method for the forecast of passenger flow because it uses a risk function consisting of the empirical error and a regularized term which is based on the structural risk minimization principle. In this paper, the prediction model of urban rail transit passenger flow is constructed. It is to build an urban rail transit passenger flow forecast model and select the optimal parameters from the support vector regression through the variable metric method to obtain the minimal value from the LOO error bounds. The passenger flow is forecast by means of both support vector regression method and BP neural network method, and the results show that the support vector regression model has such theoretical superiority as minimized structural risk, thus having a higher forecasting accuracy under small sample conditions for short-term rail transit passenger flow, which predicts the promising forecasting performance that the method has.

Full Text:




  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License