Abstract: A machine-learning method for learning a function for predicting a next feature in a feature tree. The method includes obtaining a dataset of examples each including a graph representing at least a part of a feature tree. The graph includes nodes each representing a feature and each labeled with a label of a set of labels each indicating a feature type of a predetermined set. The graph includes edges each connecting nodes and represents a parent-child relationship between the features represented by the nodes. The graph comprises ground truth data indicating a next feature according to one or more selected features each corresponding to a graph node. The method further includes training the function to take as input a graph representing at least a part of a feature tree and to output a prediction of one or more next features in the feature tree.