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
Insights articles that go deeper on ai & quantitative risk models.
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 articleThe AI-Augmented Marine Actuary
AI will not replace the marine actuary. But marine actuaries who master AI — and the governance it demands — will replace those who do not.
Read the articleModel Governance: Three Lines of Defence
Clear ownership, independent validation, and audit assurance make the difference between a model inventory that is trusted and one that is merely maintained.
Read the articleEU AI Act 2026: Transparency Duties
For financial institutions, the AI Act is less a new compliance regime than a documentation and classification problem attached to existing model governance.
Read the article