Prolog-based agnostic explanation module for structured pattern classification

This paper presents a Prolog-based reasoning module to generate counterfactual explana-tions given the predictions computed by a black-box classifier. Our approach comprises four well-defined stages that can be applied to any structured pattern classification prob-lem. Firstly, we pre-process the given dataset by imputing missing values and normalizing the numerical features. Secondly, we transform numerical features into symbolic ones using fuzzy clustering such that extracted fuzzy clusters are mapped to an ordered set of predefined symbols. Thirdly, we encode instances as a Prolog rule using the nominal val-ues, the predefined symbols, the decision classes, and the confidence values. Fourthly, we compute the overall confidence of each Prolog rule using fuzzy-rough set theory to han-dle the uncertainty caused by transforming numerical quantities into symbols. This step comes with an additional theoretical contribution to a new similarity function to compare the previously defined Prolog rules involving confidence values. Finally, we implement a chatbot as a proxy between humans and the Prolog-based reasoning module to resolve nat-ural language queries and generate counterfactual explanations. During the numerical sim-ulations using synthetic datasets, we study the performance of our system when using different fuzzy operators and similarity functions.(c) 2022 The Author(s). Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).