Skip to main content
JOJonas Osman
Data & AI

AI & Quantitative Risk Models

Machine-learning and AI models applied to credit, insurance, and financial risk — from gradient-boosting PDs and severity models to LLM-assisted risk assessment — with governance, interpretability, and model-risk controls built in from day one.

Background reading on this work: Predictive Modeling in Insurance and The AI-Augmented Marine Actuary.

Outcomes you can expect

  • AI models with lineage, monitoring, and explainability from day one
  • A governance layer aligned to SR 11-7 and EU AI Act expectations
  • Faster model iteration without piling up hidden model risk

Typical engagements

  • ML models for PD, LGD, severity, fraud, and pricing
  • Explainability layers (SHAP, PDP, surrogate models) and drift monitoring
  • AI/ML model risk framework and EU AI Act readiness
  • LLM applications for underwriting, KYC, and risk review
Related reading

Insights articles that go deeper on ai & quantitative risk models.

Browse all Insights

Other services