Decision tree learning is a machine learning technique that allows accurate and comprehensible models to be generated. Accuracy can be improved by ensemble methods which combine the predictions of a set of different trees. However, a large amount of resources is necessary to generate the ensemble. In this paper, we introduce a new ensemble method that minimises the usage of resources by sharing the common parts of the components of the ensemble. For this purpose, we learn a decision multi-tree instead of a decision tree. We call this newapproac h shared ensembles. The use of a multi-tree produces an exponential number of hypotheses to be combined, which provides better results than boosting/bagging. We performed several experiments, showing that the technique allows us to obtain accurate models and improves the use of resources with respect to classical ensemble methods.