Taxonomy and Survey of Interpretable Machine Learning Method
Saikat Das, Namita Agarwal, Deepak Venugopal, Frederick T. Sheldon, Sajjan G. Shiva
Abstract
Since traditional machine learning (ML) techniques use black-box model, the internal operation of the classifier is unknown to human. Due to this black-box nature of the ML classifier, the trustworthiness of their predictions is sometimes questionable. Interpretable machine learning (IML) is a way of dissecting the ML classifiers to overcome this shortcoming and provide a more reasoned explanation of model predictions. In this paper, we explore several IML methods and their applications in various domains. Moreover, a detailed survey of IML methods along with identifying the essential building blocks of a black-box model is presented here. Herein, we have identified and described the requirements of IML methods and for completeness, a taxonomy of IML methods which classifies each into distinct groupings or sub-categories, is proposed. The goal, therefore, is to describe the state-of-the-art for IML methods and explain those in more concrete and understandable ways by providing better basis of knowledge for those building blocks and our associated requirements analysis.