Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 10, 2025Transactions on Computer Science and Intelligent Systems Research

Comparative Analysis Research on Machine Learning Models in Credit Risk Assessment

View Full Paper
Ask AI
Bookmark
Share

Authors

BZBohan Zhang

Discussion

Loading...

Member takes

Overview

Comparative analysis reveals integrated models outperform traditional methods in credit risk assessment, suggesting improved accuracy and interpretability.

Key Points

  • Integrated models achieve an accuracy of 94% and an AUC value of 0.98 on two datasets, highlighting their superior performance.
  • Synthetic Minority Over-Sampling Technique (SMOTE) was utilized for balancing sample distributions and improving model training efficiency.
  • Feature engineering was applied, including income-debt ratio calculations, to reduce redundancy and enhance interpretability of models.
  • The use of SHAP values facilitates a clearer interpretation of model predictions, supporting better decision-making in credit risk.

Cite This Study

Bohan Zhang (2025) studied this question.

synapsesocial.com/papers/68af736e7567bf4f94fed8a9https://doi.org/10.62051/19wa7a05
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. 1DEVELOPMENT AND EVALUATION OF MACHINE LEARNING MODEL FOR LOAN DEFAULT RISK ASSESSMENT2025 · 3 citations
  2. 2Comparative Analysis of Machine Learning Models For Predicting Default in Home Credit Companies2025
  3. 3Machine Learning-Based Credit Risk Prediction: A Systematic Review of Techniques, Challenges, and Future Directions2025 · 1 citations
  4. 4AI-Driven Credit Risk Models for Small-Scale Lending: A Business Analytics Framework for Predictive Performance and Responsible Deployment2025 · 1 citations
  5. 5Explainable Artificial Intelligence Credit Risk Assessment using Machine Learning2025