Explainable AI for Interpretable Credit Scoring

TL;DR

This paper develops an accurate and interpretable credit scoring model using XGBoost, enhanced with a comprehensive explanation framework that ensures explanations are simple, consistent, and trustworthy, aligning with regulatory and practical needs.

Contribution

It introduces a novel combination of high-performance XGBoost credit scoring with a multi-faceted explanation framework for improved interpretability.

Findings

Achieved state-of-the-art accuracy on HELOC and Lending Club datasets.

Provided explanations that are simple, consistent, and meet multiple criteria.

Validated explanations through human and application-grounded evaluations.

Abstract

With the ever-growing achievements in Artificial Intelligence (AI) and the recent boosted enthusiasm in Financial Technology (FinTech), applications such as credit scoring have gained substantial academic interest. Credit scoring helps financial experts make better decisions regarding whether or not to accept a loan application, such that loans with a high probability of default are not accepted. Apart from the noisy and highly imbalanced data challenges faced by such credit scoring models, recent regulations such as the `right to explanation' introduced by the General Data Protection Regulation (GDPR) and the Equal Credit Opportunity Act (ECOA) have added the need for model interpretability to ensure that algorithmic decisions are understandable and coherent. An interesting concept that has been recently introduced is eXplainable AI (XAI), which focuses on making black-box models more interpretable. In this work, we present a credit scoring model that is both accurate and interpretable. For classification, state-of-the-art performance on the Home Equity Line of Credit (HELOC) and Lending Club (LC) Datasets is achieved using the Extreme Gradient Boosting (XGBoost) model. The model is then further enhanced with a 360-degree explanation framework, which provides different explanations (i.e. global, local feature-based and local instance-based) that are required by different people in different situations. Evaluation through the use of functionallygrounded, application-grounded and human-grounded analysis show that the explanations provided are simple, consistent as well as satisfy the six predetermined hypotheses testing for correctness, effectiveness, easy understanding, detail sufficiency and trustworthiness.