An Interpretable Model with Globally Consistent Explanations for Credit Risk

TL;DR

This paper introduces a globally interpretable neural network model for credit risk assessment that maintains high accuracy and offers transparent, consistent explanations through a decomposable additive structure and an interactive visualization tool.

Contribution

The paper presents a novel two-layer additive risk model that is both accurate and globally interpretable, with new explanation methods and an online visualization tool.

Findings

Model achieves accuracy comparable to neural networks.

Provides three types of transparent, consistent explanations.

Includes an interactive visualization tool for exploration.

Abstract

We propose a possible solution to a public challenge posed by the Fair Isaac Corporation (FICO), which is to provide an explainable model for credit risk assessment. Rather than present a black box model and explain it afterwards, we provide a globally interpretable model that is as accurate as other neural networks. Our "two-layer additive risk model" is decomposable into subscales, where each node in the second layer represents a meaningful subscale, and all of the nonlinearities are transparent. We provide three types of explanations that are simpler than, but consistent with, the global model. One of these explanation methods involves solving a minimum set cover problem to find high-support globally-consistent explanations. We present a new online visualization tool to allow users to explore the global model and its explanations.