Sheffield company partners with Nationwide to pioneer smarter AI credit scoring

Digital specialist Jaywing has joined forces with building society Nationwide to enhance the effectiveness of AI in credit scoring with its proprietary product Archetype.

In response to industry concerns around AI scoring transparency, the national financial services institution has partnered with the Sheffield based company to analyse the effectiveness of machine learning, comparing the performance of Archetype against traditional linear regression.

Analysis showed that Jaywing’s technology produced a 6 per cent increase in predictive power of application models compared with other AI-based systems, a result attributed to the company’s ability to control the neural network.

Commenting on the results, Matthew Jones, head of retail modelling at Nationwide said: “Archetype clearly represents a powerful alternative in building credit scores. We were impressed by the ease of use, the rapidly-realised benefits and ability to enforce intuitive behaviour on key variables in neural networks.

“Jaywing’s approach and depth of knowledge has made us confident that the use of neural networks and similar technologies has reached a level of maturity where it can be deployed safely within the credit risk arena.”

Based in Sheffield, Jaywing has over 19 years’ experience of credit risk analytics, and this partnership follows a history of long standing relationships with a range of financial services institutions including retail banking giants Lloyds Banking Group and Royal Bank of Scotland.

Nevan McBride, Risk Practice Director at Jaywing, added: “Across the whole credit lifecycle, from application and behavioural scoring through to debt collection, we’ve seen Archetype produce significant score improvements every time.

“In Nationwide’s case, we’ve also proven that Archetype can go head-to-head with other AI-based techniques and get a similar level of benefit…We look forward to working with Nationwide as it explores other areas of machine learning modelling.”