There is a large amount of unstructured data in the current corn cross-border supply chain system and it has the characteristics of multi-source heterogeneous. Traditional risk early warning methods have defects such as over-reliance on manual decision-making and low accuracy of early warning. In order to solve the above problems, this paper proposed a system risk early warning method of corn cross-border supply chain based on deep belief network and multi-class fuzzy support vector machine. Firstly, based on the principle of embedding coding and normalization, a large number of unstructured data in the corn cross-border supply chain system were preprocessed and converted into structured data for subsequent calculation. Then, based on the deep belief network, the high-latitude features of the data were extracted, and the change trend and correlation of risk indicators in the corn cross-border supply chain system were adaptively mined. Finally, the extracted high-dimensional features were input into the multi-class fuzzy support vector machine model for training to realize the risk classification early warning of corn cross-border supply chain. The accuracy of the algorithm proposed in this paper can reach 94.88% under the condition of similar running time. It is 52.17% higher than that of the worst algorithm, and the comprehensive performance was superior to other algorithms which can provide theoretical support for the application of system risk regulation of corn cross-border supply chain.