Unlocking the Black Box: A Five-Dimensional Framework for Evaluating Explainable AI in Credit Risk

• URL: http://arxiv.org/abs/2511.04980v1
• Date: Fri, 07 Nov 2025 04:49:29 GMT
• Title: Unlocking the Black Box: A Five-Dimensional Framework for Evaluating Explainable AI in Credit Risk
• Authors: Rongbin Ye, Jiaqi Chen,
• Abstract summary: This paper intends to fill the gap in the application between "black box" models and explainability frameworks, such as LIME and SHAP.<n>Authors elaborate on the application of these frameworks on different models and demonstrates the more complex models with better prediction powers could be applied.<n>This research demonstrates the feasibility of employing sophisticated, high performing ML models in regulated financial environments.
• Score: 17.910002088282624
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The financial industry faces a significant challenge modeling and risk portfolios: balancing the predictability of advanced machine learning models, neural network models, and explainability required by regulatory entities (such as Office of the Comptroller of the Currency, Consumer Financial Protection Bureau). This paper intends to fill the gap in the application between these "black box" models and explainability frameworks, such as LIME and SHAP. Authors elaborate on the application of these frameworks on different models and demonstrates the more complex models with better prediction powers could be applied and reach the same level of the explainability, using SHAP and LIME. Beyond the comparison and discussion of performances, this paper proposes a novel five dimensional framework evaluating Inherent Interpretability, Global Explanations, Local Explanations, Consistency, and Complexity to offer a nuanced method for assessing and comparing model explainability beyond simple accuracy metrics. This research demonstrates the feasibility of employing sophisticated, high performing ML models in regulated financial environments by utilizing modern explainability techniques and provides a structured approach to evaluate the crucial trade offs between model performance and interpretability.

Related papers

• Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws [52.10468229008941]
  This paper formalizes an emerging learning paradigm that uses a trained model as a reference to guide and enhance the training of a target model through strategic data selection or weighting.<n>We provide theoretical insights into why this approach improves generalization and data efficiency compared to training without a reference model.<n>Building on these insights, we introduce a novel method for Contrastive Language-Image Pretraining with a reference model, termed DRRho-CLIP.
  arXiv  Detail & Related papers  (2025-05-10T16:55:03Z)
• KACDP: A Highly Interpretable Credit Default Prediction Model [2.776411854233918]
  This paper introduces a method based on Kolmogorov-Arnold Networks (KANs)<n>KANs is a new type of neural network architecture with learnable activation functions and no linear weights.<n>Experiments show that the KACDP model outperforms mainstream credit default prediction models in performance metrics.
  arXiv  Detail & Related papers  (2024-11-26T12:58:03Z)
• Model-Agnostic Interpretation Framework in Machine Learning: A Comparative Study in NBA Sports [0.2937071029942259]
  We propose an innovative framework to reconcile the trade-off between model performance and interpretability. Our approach is centered around modular operations on high-dimensional data, which enable end-to-end processing while preserving interpretability. We have extensively tested our framework and validated its superior efficacy in achieving a balance between computational efficiency and interpretability.
  arXiv  Detail & Related papers  (2024-01-05T04:25:21Z)
• Stable and Interpretable Deep Learning for Tabular Data: Introducing InterpreTabNet with the Novel InterpreStability Metric [4.362293468843233]
  We introduce InterpreTabNet, a model designed to enhance both classification accuracy and interpretability. We also present a novel evaluation metric, InterpreStability, which quantifies the stability of a model's interpretability.
  arXiv  Detail & Related papers  (2023-10-04T15:04:13Z)
• Explainability for Large Language Models: A Survey [59.67574757137078]
  Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. This paper introduces a taxonomy of explainability techniques and provides a structured overview of methods for explaining Transformer-based language models.
  arXiv  Detail & Related papers  (2023-09-02T22:14:26Z)
• When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning [62.00672284480755]
  This paper aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of expertise in executing a task has applications in safety-sensitive applications such as clinical decision making and autonomous driving.
  arXiv  Detail & Related papers  (2023-02-15T04:14:20Z)
• Large Language Models with Controllable Working Memory [64.71038763708161]
  Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP) What further sets these models apart is the massive amounts of world knowledge they internalize during pretraining. How the model's world knowledge interacts with the factual information presented in the context remains under explored.
  arXiv  Detail & Related papers  (2022-11-09T18:58:29Z)
• A Framework for Auditing Multilevel Models using Explainability Methods [2.578242050187029]
  An audit framework for technical assessment of regressions is proposed. The focus is on three aspects, model, discrimination, and transparency and explainability. It is demonstrated that popular explainability methods, such as SHAP and LIME, underperform in accuracy when interpreting these models.
  arXiv  Detail & Related papers  (2022-07-04T17:53:21Z)
• Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement [75.00655434905417]
  Explainable Artificial Intelligence (XAI) is an emerging research field bringing transparency to highly complex machine learning (ML) models. This paper offers a comprehensive overview over techniques that apply XAI practically for improving various properties of ML models. We show empirically through experiments on toy and realistic settings how explanations can help improve properties such as model generalization ability or reasoning.
  arXiv  Detail & Related papers  (2022-03-15T15:44:28Z)
• Designing Inherently Interpretable Machine Learning Models [0.0]
  Inherently IML models should be adopted because of their transparency and explainability. Black-box models with model-agnostic explainability can be more difficult to defend under regulatory scrutiny.
  arXiv  Detail & Related papers  (2021-11-02T17:06:02Z)
• Explainable Matrix -- Visualization for Global and Local Interpretability of Random Forest Classification Ensembles [78.6363825307044]
  We propose Explainable Matrix (ExMatrix), a novel visualization method for Random Forest (RF) interpretability. It employs a simple yet powerful matrix-like visual metaphor, where rows are rules, columns are features, and cells are rules predicates. ExMatrix applicability is confirmed via different examples, showing how it can be used in practice to promote RF models interpretability.
  arXiv  Detail & Related papers  (2020-05-08T21:03:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.