mlsanityData to 14 Oct 2026

An Interpretable Model with Globally Consistent Explanations for Credit Risk

arXiv 1811.12615 ↗First posted 30 Nov 2018cs.LG stat.MLcited by 33

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 10; 2022: 10; 2023: 6; 2024: 3; 2025: 3; 2026: 1.

33 papers.

Sort:

By area:

  1. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 367
  2. 2021On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Resultscited by 32
  3. 2023GLOBE-CE: A Translation-Based Approach for Global Counterfactual Explanationscited by 27
  4. 2024Elephants Never Forget: Testing Language Models for Memorization of Tabular Datacited by 19
  5. 2021A Holistic Approach to Interpretability in Financial Lending: Models, Visualizations, and Summary-Explanationscited by 16
  6. 2023Recourse under Model Multiplicity via Argumentative Ensembling (Technical Report)cited by 15
  7. 2023A Review of the Role of Causality in Developing Trustworthy AI Systemscited by 14
  8. 2021Explainability Is in the Mind of the Beholder: Establishing the Foundations of Explainable Artificial Intelligencecited by 13
  9. 2022Monotonic Neural Additive Models: Pursuing Regulated Machine Learning Models for Credit Scoringcited by 12
  10. 2022Trade-off Between Efficiency and Consistency for Removal-based Explanationscited by 6
  11. 2024Reconciling Model Multiplicity for Downstream Decision Makingcited by 5
  12. 2024Gradient Boosting Trees and Large Language Models for Tabular Data Few-Shot Learningcited by 5
21 more
  1. 2021Extrapolation Frameworks in Cognitive Psychology Suitable for Study of Image Classification Modelscited by 4
  2. 2022Computing Rule-Based Explanations by Leveraging Counterfactualscited by 4
  3. 2023Monotonicity for AI ethics and society: An empirical study of the monotonic neural additive model in criminology, education, health care, and financecited by 4
  4. 2021Unpacking the Black Box: Regulating Algorithmic Decisionscited by 3
  5. 2021Score-Based Explanations in Data Management and Machine Learning: An Answer-Set Programming Approach to Counterfactual Analysiscited by 2
  6. 2022Generalized Groves of Neural Additive Models: Pursuing transparent and accurate machine learning models in financecited by 2
  7. 2022Interpretable Selective Learning in Credit Riskcited by 2
  8. 2022RbX: Region-based explanations of prediction modelscited by 2
  9. 2023Attribution-Scores and Causal Counterfactuals as Explanations in Artificial Intelligencecited by 2
  10. 2023Attribution-Scores in Data Management and Explainable Machine Learningcited by 2
  11. 2021LEx: A Framework for Operationalising Layers of Machine Learning Explanationscited by 1
  12. 2022To what extent should we trust AI models when they extrapolate?cited by 1
  13. 2025Argumentative Ensembling for Robust Recourse under Model Multiplicitycited by 1
  14. 2025On Arbitrary Predictions from Equally Valid Modelscited by 1
  15. 2021Distilling Interpretable Models into Human-Readable Codecited by 0
  16. 2021Federated Artificial Intelligence for Unified Credit Assessmentcited by 0
  17. 2022Constructive Interpretability with CoLabel: Corroborative Integration, Complementary Features, and Collaborative Learningcited by 0
  18. 2022A Concept and Argumentation based Interpretable Model in High Risk Domainscited by 0
  19. 2022Interpretable ML for Imbalanced Datacited by 0
  20. 2025Integrating Transparent Models, LLMs, and Practitioner-in-the-Loop: A Case of Nonprofit Program Evaluationcited by 0
  21. 2026Context-Adaptive Thresholding for Conditionally Representative Monitoring and Classificationcited by 0