The deficiency of current methods for predicting the airport total cargo was analysed and the grey support vector machine combination model was introduced to predict the airport total cargo.The ratio sequence of the actual values to the results predicted by the gray model was regarded as an input of the support vector machine model,and the radial basis function was selected as a kernel function.By use of crossvalidation method the optimal parameter was searched.The support vector machine model was then applied to predict the real ratio sequence,and finally the result was restored to the value of the airport total cargo by using again the gray model.The total cargo of Shanghai airport was taken as an example to illustrate the feasibility of the model,and its results were compared with those predicted by the gray model and the support vector machine model.