Project Ellipse explores the use of ISDA’s Common Domain Model to digitally extract, query and analyse large quantities of data in real-time for supervisory purposes.
The BIS Innovation Hub has unveiled a new project that will explore how supervision could become more insights-based and data-driven using an integrated regulatory data and analytics platform.
Project Ellipse is a PoC which, if implemented, would be used by regulatory authorities to digitally extract, query and analyse large quantities of data from diverse sources. The data would be visible in real-time via dashboards, informing regulators of early supervisory actions that may need to be taken.
The platform is being developed in two phases. For Phase 1, the BIS Innovation Hub has partnered with MAS (Monetary Authority of Singapore), the BOE (Bank of England) and ISDA (International Swaps and Derivatives Association) to explore the concept of cross-border digital regulatory reporting, using a machine executable data model.
Reporting platforms built on common data models offer the possibility that global financial reporting entities can fulfil cross-border reporting obligations using a common input layer, the BIS says. “This would reduce compliance burdens placed on those financial institutions to respond to template-based regulatory reporting requests from different supervisory regimes for similar exposures.”
“It would also enable home and host supervisors of these global reporting entities to compare exposures in a more consistent and transparent way.”
To obtain a common understanding of the data collected for regulatory purposes across reporting regimes, the project reviewed reporting requirements for retail mortgages in the UK and Singapore, to derive a subset of granular data attributes from those requirements.
The data attributes were modelled using ISDA’s CDM (Common Domain Model), an open-source, standardised, machine-readable and machine-executable model used for OTC derivatives, cash securities, securities financing and commodities.
The use of the CDM in the PoC demonstrated the feasibility of extending an existing globally applicable derivatives data model to retail mortgages, where executable code generated from the model’s definitions enabled the automation of regulatory mortgage data for Singapore and the UK, referencing the same common model.
Phase 1 of the project illustrates the efficiencies that can be gained when adopting machine executable reporting using common data models, the BIS says.
Phase 2 of the project will explore the integration of granular data sets with unstructured data, using artificial intelligence and machine learning to extract insights from data to highlight correlations between current events and supervisory metrics.
The insights extracted would then be displayed as early warnings for supervisory attention via dashboards.