A Categorisation of Post-hoc Explanations for Predictive Models

TL;DR

This paper extends and tests a categorisation of post-hoc explanation techniques for predictive models, addressing the need for interpretability in machine learning applications across various domains.

Contribution

It provides an expanded categorisation framework for post-hoc explanations and empirically evaluates its applicability and effectiveness.

Findings

The categorisation effectively groups diverse explanation methods.

Certain explanation techniques are more suitable for specific model types.

The framework aids in selecting appropriate interpretability tools.

Abstract

The ubiquity of machine learning based predictive models in modern society naturally leads people to ask how trustworthy those models are? In predictive modeling, it is quite common to induce a trade-off between accuracy and interpretability. For instance, doctors would like to know how effective some treatment will be for a patient or why the model suggested a particular medication for a patient exhibiting those symptoms? We acknowledge that the necessity for interpretability is a consequence of an incomplete formalisation of the problem, or more precisely of multiple meanings adhered to a particular concept. For certain problems, it is not enough to get the answer (what), the model also has to provide an explanation of how it came to that conclusion (why), because a correct prediction, only partially solves the original problem. In this article we extend existing categorisation of techniques to aid model interpretability and test this categorisation.