Features for black-box machine-learning models

Abstract

A method for enabling a transformation system, comprising a transformation model built for a first setting using first input values, to incorporate second feature values present in a second setting is disclosed. The method comprises providing training input data comprising second feature values as well as expected second results, providing a feature mapper comprising a machine-learning model, wherein output signals of the feature mapper are used as input signals for the transformation system, thereby building a combination of the feature mapper and the transformation model, training of the machine-learning model of the feature mapper using the training input data as input for the feature mapper and using the second results as expected output data of the transformation system, and deploying the combination of the feature mapper and the transformation system as a super machine-learning system comprising a super machine-learning model usable in the second setting.