Leeds Building Society has adopted new AI-based technology to predict missing Energy Performance Certificate (EPC) data and accurately evaluate the emissions of its mortgage portfolio.

The software, from 4-Xtra Technologies, therefore enables the society to incorporate environmental, social and governance (ESG) considerations into credit decisioning and risk management processes for mortgages.

However, not all properties have a valid EPC, which means the data has to be estimated.

4-Xtra, which was spun out from Leeds University, uses what it calls an ‘extreme event forecasting engine and complementary synthetic data generator’ to estimate what the missing data is.

Leeds Building Society chief risk officer Andy Mellor says: “Missing EPC data was a particular obstacle in meeting these requirements for our mortgage portfolio. The successful proof of concept undertaken with 4-Xtra Technologies and its Software as a service solution has demonstrated that we can now instantly estimate data for any gaps, which in turn improves our credit decisioning processes and enables us to report our mortgage portfolio emissions more accurately.”

4-Xtra Technologies chief executive David Potter adds: “We are working on providing further enhancements to our solution, to include other physical risks while also actively developing other financial services solutions using our extreme event forecasting and synthetic data generation technology.”