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.

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

Predictive Modeling in Insurance

Predictive modeling has quietly reshaped insurance pricing. Here's what actually works, what to watch out for, and how to keep models explainable to regulators.

Read the article

Other services