Railway passenger flow is affected by many factors, and its timing characteristics are obvious. Therefore, Based on the stationary time series, passenger flow data prediction model and single-ride multi-interval ticket distribution model were constructed., which is beneficial to grasp the dynamic changes of passenger flow and improve the railway operation pressure. The characteristic data extraction system is developed, and carried out data preprocessing such as accumulation, cycle and screening algorithm. Analysis of variance was used to evaluate the significant correlation effect of various factors, the ARMA model was used to predict the short-term passenger flow. The model is optimized and tested. Meanwhile, Based on linear programming, an optimal model of interval ticket allocation for load factor maximization is constructed.