Generating Fuzzy Queries from Weighted Fuzzy Classifier Rules

Abstract This work ,presents a methodology ,to generate automatically a set of fuzzy queries that are translated from a set of fuzzy rules learned from a data set. A rule simplification approach is proposed, which allows a better interpretability of ,the fuzzy query sentence. The fuzzy query sentences are generated in such a way ,that they can be processed by a,standard fuzzy query system. The methodology is applied to a ,benchmark data set considering a scenario ,of target selection in a ,direct market application. The results obtained by the current approach are compared with the results of a standard a decision tree induction algorithm.