Steve describes a method of classifying nodes in an information network by application of a non-Euclidean convolutional neural network. The convolutional layers are kerneled to operate directly on the natural manifold of the information space, and thus produce output more accurate than analysis on information arbitrarily embedded in a Euclidean geometry. First, Steve describes the benefits of operating in a non-Euclidean geometry. He then sketches out how graph convolutional networks work. Finally, Steve demonstrates the application of this technique by predicting the credit-worthiness of applicants based on their population characteristics and their relationships to other individuals.