By analyzing the influence factors of railway passenger traffic from 1997 to 2007, partial least-squares regression model were established, then actual and predicted values of railway passenger traffic were compared, and the model prediction error was relatively high. In order to improve the prediction accuracy of the model, PSO optimization algorithm was adopted to optimize the regression coefficients, then a new model was got. Upon examination, the prediction error of the model dropped to 1.01%from original 3.04%. Finally the railway passenger traffic from 2013 to 2014 which we use this mode...
