• An artificial intelligence (AI) application developed by the Bank for International Settlements (BIS) and its project partners, the Bank of Spain, the Deutsche Bundesbank and the European Central Bank, enables analysis of climate-related risks in the financial system.
• Project Gaia created a proof of concept and tested it in financial climate risk analysis use cases. 
• The proof of concept used large language models (LLMs) to automatically extract climate-related indicators from publicly available corporate reports.

Project Gaia, an initiative of the BIS Innovation Hub and the Bank of Spain, the Deutsche Bundesbank and the European Central Bank, has leveraged AI to enable the comprehensive analysis of climate-related risks in the financial system.

Central banks, supervisors and financial institutions need high-quality and accessible data to model the financial risks posed by climate change. A lack of global reporting standards makes this difficult. The project report describes how Gaia was able to overcome differences in definitions and disclosure frameworks across jurisdictions to offer much-needed transparency and make it easier to compare information on climate-related financial risks. 

The experiment was coordinated by the BIS Innovation Hub Eurosystem Centre and aimed to help analysts and supervisors search corporate climate-related disclosures and extract data quickly and efficiently on indicators such as total emissions, green bond issuance and voluntary net-zero commitments. Using AI and, in particular, LLMs, Gaia delivered a proof of concept demonstrating it is possible to automate the task of identifying such indicators across a large set of reports, significantly reducing manual effort in climate assessments. 

Gaia has broken new ground by integrating LLMs into an application and using it for the extraction of data on climate-related financial risks. The flexible design may serve as a model for AI-enabled applications in a broader range of use cases for central banks and the financial sector. 

With Gaia, the BIS and the Eurosystem are not just keeping pace with digitalisation; we are experimenting in driving it forward, integrating AI with a clear vision for a more resilient landscape and allowing us to rapidly address newly emerging risks.” 

Agustín Carstens, General Manager of the BIS 

It is inspiring to see real-life examples of how collaboration can solve common challenges. Project Gaia is an important breakthrough on the road to the understanding and adaptation of AI into the innovation culture of the Eurosystem. The potential applications and synergies of this tool are nearly limitless.”

Pablo Hernández de Cos, Governor of Bank of Spain

Project Gaia makes assessing climate risk more transparent and efficient, as it uses generative AI to decipher vast unstructured data sets. If realised, Gaia has the potential to be a powerful tool for central banks in their comprehensive approach to assessing economic reality and risks.”

Christine Lagarde, President of European Central Bank

In today’s data-driven world, the challenge isn’t just gathering information; it’s making sense of it. Gaia tackles this challenge, transforming unstructured data into actionable insights. By leveraging large language models, Gaia empowers central banks to better navigate the complexities of sustainability reporting.”

Joachim Nagel, President of Deutsche Bundesbank

The BIS Innovation Hub is at the forefront of technology innovation for central banks. With Gaia, we provide a powerful tool for climate risk analysis and explore how generative AI can automate workflows and enhance the stability of the financial system.” 

Cecilia Skingsley, Head of the BIS Innovation Hub 

Project Gaia showcased the potential of generative AI to streamline central bank operations. By automating and refining data processes, generative AI can change the way we work, offering a blueprint for efficient, data-driven progress,” 

Raphael Auer, Head of the Eurosystem Centre, BIS Innovation Hub

Note to editors:

BIS Innovation Hub projects are experimental in nature, for the purpose of investigating technological and practical feasibility.