BIS Innovation Hub, MAS develop prototype supervisory analytics platform
The BIS Innovation Hub Singapore Centre and the Monetary Authority of Singapore (MAS) have developed a new prototype platform that integrates regulatory data and analytics. Known as Project Ellipse, the platform successfully demonstrates how regulatory and other data, such as articles and news, can be integrated into a single platform to help regulatory authorities identify potential risks to individual banks and the banking system.
To enable collaboration, the BIS will launch an Ellipse collaboration community to share, further test, customise and scale this solution across regulatory authorities around the world. The Ellipse prototype is the first to be published on BIS Open Tech , a new platform for sharing statistical and financial software as public goods, thereby promoting international cooperation and coordination.
“Regulators need accurate and timely information to assess emerging risks and to make informed supervisory decisions. Project Ellipse has now developed a potential tool for the global regulatory community to further explore and collaborate on common solutions that can improve the data and analytical capabilities of regulatory authorities. It has the potential to be a game-changer by giving supervisors access to more and better data, structured and unstructured, with greater predictive insights than ever before, it can be scaled to provide real time analysis on a national or cross border supervisory basis”, said Ross Leckow, Acting Head of the BIS Innovation Hub.
With the support of the Bank of England, the International Swaps and Derivatives Association, Accenture and Financial Network Analytics, the project was undertaken in two phases:
- Phase one of the project investigated how machine executable digital reporting could enable data-driven supervision, using a cross-border common data model.
- Phase two examined how advanced analytics such as machine learning and natural language processing could be applied to unstructured and granular reporting data. This allows identification of risk correlations and sentiment analysis, so as to alert supervisors in real time to issues that may need further investigation.