Virgin Money tests Jaywing AI technology to enhance risk models

Virgin Money worked with data science expert, Jaywing, to deploy Artificial Intelligence (AI) tests with its award-winning AI software, Archetype in its credit card business. Archetype’s AI-based modelling enables Virgin Money to gain a deeper understanding of its customers, so that it can further improve the customer experience and enhance risk modelling.

Developments in AI have put more advanced, AI-based credit and fraud scores within scope for most lenders. It’s now possible to deploy explainable, controlled models which squeeze more value from data than ever before – reducing fraud and credit risk, maximising profitability, and optimising acceptance rates – whilst being fully compliant with regulatory requirements.

Through the use of Archetype models, Virgin Money can identify which customers are most likely to consider switching credit card provider with more accuracy than ever before. This enables the bank to tailor marketing and promotional offers based on individual customer circumstances, improving the customer experience and reducing the likelihood of customers deciding to switch providers.

“The Archetype fraud model is the best of the lot, giving us an exceptionally strong weapon in the fight against financial crime in the application space.”

Nick Martin, Head of Analytics, Virgin Money Credit Card

Compared with existing models (built on the same data sample), Archetype delivered a double-digit improvement in the ability to predict customers most likely to leave.

Jaywing also ran a proof of concept to demonstrate the potential of Archetype’s AI capabilities to enhance credit risk models. Virgin Money has built a high-quality credit card book with the existing scorecard approach. Running alongside this traditional risk model, the Archetype model combined internal data and bureau information to demonstrate the potential for AI to even more accurately assess credit risk and predict low risk applications. More precise profiling of applications provides the ability to make even more accurate lending decisions, with the potential to reduce bad debt while taking on more customers.

Meanwhile, Archetype delivered an application fraud model with:

  • A predictive power of 93% for Virgin Money
  • Offered a relative uplift of 31% over the incumbent approach
  • Detected over 86.6% of fraud cases by reviewing just the top 10% of cases