Learning Preferences for Collaboration

ABSTRACT. In this paper we propose the acquisition of a set of preferences of collaboration between classifiers based on decision trees. A classifier uses $k$-NN with leaf-one-out on its own knowledge base to generate a set of tuples with information about the object to be classified, the number of similar precedents, the maximum similarity, and about if it is a situation of collaboration or not. We considered that a classifier does not collaborate when it is able to reach by itself the correct classification for an object, otherwise it has to collaborate. These tuples are given as input to generate a decision tree from which a set of collaboration preferences is obtained.