Explaining Classification by Finding Response-Related Subgroups in Data

Abstract--A method for explaining results of a regressionbased classifier is proposed. The data is clustered using a metric extracted from the classifier. This way, clusters found are related to classifier predictions, and each cluster can be considered a possible explanation for classification result. The clusters are described by simple rules, meant to be easy for a human to understand. The key points of the work are presenting a modular framework for explaining the classification, and studying and comparing two different approaches for extracting a metric from a classifier model. Keywords-data abstraction, supervised clustering, MLP classifier, subgroup rules

• Type: Conference
• Year: 2010
• Where: SNPD
• Authors: Elina Parviainen, Aki Vehtari
• Keywords: Artificial Intelligence, Classifier Predictions, Possible Explanation, Regressionbased Classifier, SNPD 2010