Objective：According to the seasonal and trend epidemic phenomenon of hepatitis E，the multiple seasonal ARIMA model was established to predict the infectious incidence of hepatitis E in China. Methods：SPSS23.0 software was used to model the monthly data of the epidemic of hepatitis E infectious diseases in China from January 2004 to June 2018，so as to predict the incidence of hepatitis E in the second half of 2018 and to evaluate the prediction effect of the model through the epidemic data during the period. Results：The average values of the prediction of the two models，ARIMA（2，1，0）（0，1，1）12 and ARIMA（0，1，2）（0，1，1）12，were used as the prediction values，the average relative error of the prediction was 4.69% and the standard deviation was 3.27%. Conclusion：Results of fitting and prediction of the multiple seasonal ARIMA model are good. The model can better describe the incidence trend of hepatitis E in China during the period，and provide certain scientific basis for the formulation of preventive control measures against hepatitis E and reasonable allocation of health resources.