Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 13, 2025Open Access

Enhancing ML Models Interpretability for Credit Scoring

View Full Paper
Ask AI
Bookmark
Share

Authors

SSSamuel D. SchwartzQWQinling WangFFFang Fang

Discussion

Loading...

Member takes

Overview

Hybrid approach enhances feature selection and model interpretability in credit scoring, indicating regulatory compliance.

Key Points

  • This approach achieves performance comparable to black-box models while reducing feature use by 88.5%.
  • SHapley Additive exPlanations is utilized for feature selection, optimizing model transparency and power.
  • Glass-box models, like Explainable Boosting Machine, ensure regulatory compliance through enhanced interpretability.
  • Feature interaction analysis further strengthens the model's robustness and explanatory capabilities.

Cite This Study

Schwartz et al. (2025) studied this question.

synapsesocial.com/papers/68ecfebf950606aabec09482https://doi.org/10.48550/arxiv.2509.11389
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Explainable Artificial Intelligence for Credit Risk Assessment: Balancing Transparency and Predictive Performance2025 · 3 citations
  2. 2Credit Risk Modeling with Explainable AI: Predictive Approaches for Loan Default Reduction in Financial Institutions2021 · 17 citations
  3. 3Explainable Artificial Intelligence Credit Risk Assessment using Machine Learning2025
  4. 4Enhancing Scalability and Transparency in AI-Driven Credit Scoring: Optimizing Explainability for Large-Scale Financial Systems2025 · 3 citations
  5. 5Credit Risk Analysis using Explainable Artificial Intelligence2024 · 2 citations