Test and training data

A method, apparatus and computer-readable instructions are described including obtaining a plurality of sets of training and test data packages (wherein: each of the plurality of sets comprises test data and training data, wherein the test data comprises a subset of a first plurality of data items and the training data comprises a remainder of the first plurality of data items; each data item of the first plurality of data items is allocated as test data for only one of the plurality of sets of training and test data packages; and each data item comprises a classification identifier); receiving a new data item having a classification identifier; and adding the new data item to one of the plurality of sets of training and test data packages as test data and adding the new data item to the other of the plurality of sets of training and test data packages as training data, wherein the one of the plurality of sets of training and test data packages to which the new data item is added as test data is selected depending on the classification identifier of the new data item and the classification identifiers of the first plurality of data items.