Abstract: To solve the unbalanced bus passenger flow during weekday rush hours in China's big cities, a multiple linear regression model is established by collecting the bus IC card data, weather data and line data, considering the weather types, temperature and wind factors which influence the passenger flow. The results show that the model can forecast, quickly and precisely, the bus weekday passenger flow in each peak period, which may provide the basis for reasonably scheduling bus passenger flow.

Key words: IC card data, multiple linear regression, passenger flow forecast