Influential Factor Analysis and Prediction on Initial Metro Network Ridership in Xi’an, China

To satisfy the adaptability of forecasting short-term and abrupt volume initial metro network, we build multiple enter linear regression (MELR) model to explore determinants forecast intensity during twice expansion network in Xi’an. We further compare prediction transport capacity between MELR models with exponential smoothing autoregressive integrated moving average (ARIMA) models. Results show that passenger significantly fluctuates months days, is more adapted for than ARIMA new line opening old expands, which avoids drawback time series need a huge database. This study provides guide accurate purchase rail vehicles planning expends stages.