PermuteAttack: Counterfactual Explanation of Machine Learning Credit Scorecards

TL;DR

This paper introduces PermuteAttack, a framework using adversarially generated counterfactual examples to explain and validate machine learning credit scoring models, especially for tabular financial data.

Contribution

It presents a novel gradient-free genetic algorithm approach for generating realistic counterfactuals in tabular data, enhancing model interpretability and robustness assessment.

Findings

Effective generation of realistic counterfactuals for tabular data.

Provides black-box explanations of model behavior.

Identifies regions where model performance deteriorates.

Abstract

This paper is a note on new directions and methodologies for validation and explanation of Machine Learning (ML) models employed for retail credit scoring in finance. Our proposed framework draws motivation from the field of Artificial Intelligence (AI) security and adversarial ML where the need for certifying the performance of the ML algorithms in the face of their overwhelming complexity poses a need for rethinking the traditional notions of model architecture selection, sensitivity analysis and stress testing. Our point of view is that the phenomenon of adversarial perturbations when detached from the AI security domain, has purely algorithmic roots and fall within the scope of model risk assessment. We propose a model criticism and explanation framework based on adversarially generated counterfactual examples for tabular data. A counterfactual example to a given instance in this context is defined as a synthetically generated data point sampled from the estimated data distribution which is treated differently by a model. The counterfactual examples can be used to provide a black-box instance-level explanation of the model behaviour as well as studying the regions in the input space where the model performance deteriorates. Adversarial example generating algorithms are extensively studied in the image and natural language processing (NLP) domains. However, most financial data come in tabular format and naive application of the existing techniques on this class of datasets generates unrealistic samples. In this paper, we propose a counterfactual example generation method capable of handling tabular data including discrete and categorical variables. Our proposed algorithm uses a gradient-free optimization based on genetic algorithms and therefore is applicable to any classification model.