Cookies on this website
We use cookies to ensure that we give you the best experience on our website. If you click 'Continue' we'll assume that you are happy to receive all cookies and you won't see this message again. Click on 'Find out more' to see our Cookie statement.
Test bed description

In collaboration with external financial partners, this project is developing a benchmarking tool to allow investors to understand and quantify the biodiversity impacts of investment portolios. The approach combines machine learning, natural language processing, and causal inference on large-scale open-source datasets - including global news coverage - to identify the causal chains of biodiversity impacts from corporate activity, and produce a 'biodiversity risk score' for a given investment portfolio. The tool has already attracted much interest and has a strong reputation, but is currently constrained in terms of technology capabilities with regard to AI, data science and analytics on a large scale. The aim of this test bed is to increase viability and accuracy of the approach, and bring forward the chance to demonstrate the results to existing interested external parties who have a desire to incorporate biodiversity risk considerations into their investment strategies.

PIs: Joss Wright, EJ Milner-Gulland

Related themes