Journal article

Exploiting patterns to explain individual predictions

Y Jia, J Bailey, K Ramamohanarao, C Leckie, X Ma

Knowledge and Information Systems | Springer London | Published : 2020

Abstract

Users need to understand the predictions of a classifier, especially when decisions based on the predictions can have severe consequences. The explanation of a prediction reveals the reason why a classifier makes a certain prediction, and it helps users to accept or reject the prediction with greater confidence. This paper proposes an explanation method called Pattern Aided Local Explanation (PALEX) to provide instance-level explanations for any classifier. PALEX takes a classifier, a test instance and a frequent pattern set summarizing the training data of the classifier as inputs, and then outputs the supporting evidence that the classifier considers important for the prediction of the ins..

View full abstract