For the perpose of guarantee the normal take-off of aircraft, improve the operating income of airline companies and reduce the cost of aviation material guarantee, to address the problem that it is difficult to forecast aviation material consumption with small sample size and large variation, a time series-based support vector machine regression material consumption forecast model is proposed, and grid search is used to find the optimization of model parameters. Taking the actual consumption data of a domestic civil aircraft as an example, the forecast accuracy of the support vector machine regression method is verified, and the results prove that the method has good adaptability to small sample data and has higher forecast accuracy compared with the exponential smoothing method.