Objective：To investigate the epidemiologic characteristics of syphilis，establish an Autoregressive Integrated Moving Average Model(ARIMA) model for the prediction of monthly incidence of syphilis in Jiangsu and provide evidence for the prevention and control of the disease. Methods：We used monthly incidence data of syphilis in Jiangsu from 1995 to 2009 to establish the ARIMA model，and then evaluated the model. Results：ARIMA(1，1，0)，(2，1，0) models are the optimal models to predict the monthly incidence of syphilis in Jiangsu，the coefficients of recurrent model，seasonal first-order model，seasonal second-order model respectively are -0.579，-0.245，-0.357，statistics of t test respectively are 8.777，2.881，4.766. Correspondingly，the values of P respectively are 0.000，0.005，＜0.001. The model had favorably high precision，the predicting value was close to the true value，which was with in the 95% confidence interval of the predicting value. Conclusion：The ARIMA model was suitable to forecast the incidence of syphilis.ARIMA model could be used to predict the incidence trend of syphilis and provide evidence for the development of syphilis prevention and control measures.