MANAGING RISK IS A CONTINUOUS JOURNEY
Whether due to your own risk appetite, or in response to the increasing pace of regulatory change, managing risk is a continuous journey. We deliver best-in-class analytics and consulting to ensure organisations of all industries, sizes and complexities optimise profits and achieve regulatory compliance.
-
Exploring Nationwide's ‘explainable’ AI-driven application scoring
-
Transforming onboarding processes for Together
-
Implementing Data Governance and Data Management for England’s Largest Specialist Housing and Care Provider
-
Starling Bank appoints Jaywing to build a robust IFRS 9 model framework for its CBILS
Discover Archetype
Use explainable and controllable AI to generate models with greater accuracy, speed and precision than ever before.
Find out moreModernising credit-risk models without drifting outside risk appetite
Modernising credit risk models: how lenders can introduce explainable ML without weakening governance or drifting outside risk appetite.
Identifying hidden fraud networks: Why fraud detection needs a network-based approach
Fraud is now networked. Learn how graph databases help detect fraud rings, reduce losses and improve real-time decision making.
Sample size and model choice: When GBMs outperform DNNs in credit risk
When do GBMs outperform DNNs in credit risk modelling? New research shows how sample size and number of defaults influence machine learning model performance.
Smarter fraud and AML convergence: Escaping the silos
Why fraud and AML separation weakens detection and what unified, graph-based architecture requires by 2026.
Geopolitical shocks and credit risk: Are your models ready?
How geopolitical realignment challenges credit risk forecasting. Lessons from climate risk modelling and the 2025 BCST for UK banks and risk teams.
Machine learning model stability: Do Gradient Boosting Machines (GBMs) and Deep Neural Networks (DNNs) really degrade faster?
Machine learning models often outperform early, but what happens after go-live? We look at long-term performance of GBMs and DNNs using multi-year credit data.
