Accurate and Intuitive Contextual Explanations using Linear Model Trees

TL;DR

This paper introduces a novel approach for explaining complex machine learning models in finance by combining GAN-generated synthetic data with Linear Model Trees to produce more accurate and intuitive local explanations.

Contribution

It proposes using GANs for synthetic data generation and Linear Model Trees as surrogates, enhancing the quality and interpretability of local explanations over existing methods.

Findings

Improved explanation accuracy with GAN-generated data

Enhanced interpretability through Linear Model Trees

Provides contextual explanations alongside feature attributions

Abstract

With the ever-increasing use of complex machine learning models in critical applications within the finance domain, explaining the decisions of the model has become a necessity. With applications spanning from credit scoring to credit marketing, the impact of these models is undeniable. Among the multiple ways in which one can explain the decisions of these complicated models, local post hoc model agnostic explanations have gained massive adoption. These methods allow one to explain each prediction independent of the modelling technique that was used while training. As explanations, they either give individual feature attributions or provide sufficient rules that represent conditions for a prediction to be made. The current state of the art methods use rudimentary methods to generate synthetic data around the point to be explained. This is followed by fitting simple linear models as surrogates to obtain a local interpretation of the prediction. In this paper, we seek to significantly improve on both, the method used to generate the explanations and the nature of explanations produced. We use a Generative Adversarial Network for synthetic data generation and train a piecewise linear model in the form of Linear Model Trees to be used as the surrogate model.In addition to individual feature attributions, we also provide an accompanying context to our explanations by leveraging the structure and property of our surrogate model.