Find out about our DataSprint where teams collaborated on synthetic ecosystem of financial data creations.
Our 3-week DataSprint in July and August 2020 brought together 120 participants from across regulated firms, start-ups, academia, professional services, data scientists and subject matter experts. They collaborated on developing high-quality synthetic financial datasets to be used by participants in our forthcoming digital sandbox pilot.
The digital sandbox[1] will enable innovative firms to test and develop proofs of concept in a digital testing environment around 3 use cases related to coronavirus (Covid-19):
- detecting and preventing fraud and scams
- supporting the financial resilience of vulnerable consumers
- improving access to finance for small and medium-sized enterprises
The creation of a synthetic ecosystem of financial data is a highly ambitious and complex task. During the DataSprint, participants made significant progress in developing data models and typologies, evaluating methodologies and producing reference data for millions for synthetic individuals and businesses.
Beyond the immediate task of developing synthetic data assets for the digital sandbox pilot, we hope the event will be a catalyst for collaboration around the development of synthetic data assets in the financial services industry.
We’re grateful to everyone who volunteered their time and expertise to work towards a public good.
Over 50 participants have continued working since the sprint, refining and expanding the data assets produced. In the coming weeks, once this work is completed, we will open applications for the digital sandbox.
Thank you to everyone for your contribution.