Background
For assessing companies’ climate change risk, stakeholders cannot rely solely on quantitative data (e.g. GHG emissions). The narrative, mainly available in text form, that corresponds to the quantitative data is at least as important, if not even more. However, for stakeholders who need to track several hundred companies, manual analysis is out of the question. They depend on a scalable, consistent, and efficient approach.
Objective
The project started in 2019 with the overall aim to make climate-related unstructured textual information from various sources available for research, policy-making, financial supervisory authorities, and financial analysts. At its core, this involves quantifying qualitative data, such as TCFD reporting by companies, for further analysis. While the accounting and finance literature often relies on rule-based or simple machine learning approaches for this task, we use state-of-the-art deep learning approaches such as Transformer for this purpose.