AI-Driven Credit Scoring#

Research on machine learning approaches to credit risk assessment and lending decisions.

Overview#

Credit scoring is a critical application of AI in finance, determining access to credit for millions of consumers and businesses. The FinAI network investigated:

  • Advanced ML models for credit risk
  • Fairness and bias in credit decisions
  • Alternative data sources
  • Regulatory compliance

Key Research Areas#

  1. Model Development

    • Gradient boosting and ensemble methods
    • Neural networks for credit risk
    • Survival analysis approaches

  2. Fairness and Ethics

    • Bias detection and mitigation
    • Fair lending compliance
    • Algorithmic discrimination

  3. Alternative Data

    • Social media signals
    • Transaction data analysis
    • Mobile phone usage patterns

  4. Regulatory Compliance

    • Model documentation requirements
    • Adverse action explanations
    • Stress testing frameworks

Working Group#

This topic was investigated by WG2: Transparent versus Black Box Decision-Support Models.

WG2 Leader: Prof. Petre Lameski (North Macedonia)

  • Explainable AI in Credit Risk Management
  • Fair Credit Scoring with Machine Learning
  • Alternative Data in Consumer Lending

(c) Joerg Osterrieder 2025

Backward Blockchain Analytics Explainable AI in Finance Forward