Stockholm (NordSIP) – One of the main challenges facing sustainable investors revolves around the nature of ESG data and how it can be interpreted and used. Now, Sweden’s Länsförsäkringar announced it is exploring the question through a new research project that applies artificial intelligence (AI) to responsible investment called “ESG prediction”.
Länsförsäkringar Forskningsfond funds the research on AI and responsible investments, which is conducted via a partnership between Länsförsäkringar Liv, Stockholm University, Gävle University and via the Center for Research on Economic Relations (CER) at Mid Sweden University. The research examines the application of AI in handling unstructured sustainability information and how it can contribute to the investment process within Länsförsäkringar Liv’s asset management, in particular by predicting companies’ sustainability risks.
According to Kristofer Dreiman, Head of Responsible Investments at Länsförsäkringar Liv, the goal of the “ESG prediction” project is to identify companies with high sustainability risks, explain why and then use the results as a basis for further analysis or advocacy work. He explains that the results from previous research vary due to methodological differences and the lack of consensus, while also noting that the practice of aggregating values into an overall assessment of the companies analysed complicates the analysis.
Initially, the research project started by analysing the relationship between companies’ ESG ratings and how exposed they are to getting involved in controversies. The researchers found a low correlation between the environmental ratings and the risk of an environmental controversy, which means that companies with relatively high ratings still have a high risk of getting involved in environmental controversies. Previous research and the new results confirm the need for new and alternative methods that can differentiate companies based on maturity in sustainability work and sustainability risks.
Dreiman explains that after the initial phase, the project is now investigating how it is possible to use AI and machine learning to find patterns and connections between environmental indicators and environmental controversies, for example. With the help of historical data and patterns, these values could predict companies’ sustainability risks, Dreiman says.