ESG & AI / Machine Learning Use Cases

Environmental, social, and governance (ESG) factors are a set of standards used to evaluate a company’s performance on issues that have an impact on society and the environment. AI or machine learning can be used to help identify these factors. In this blog post, we will explore some use cases for how AI / machine learning can be used in conjunction with ESG factors.

The following is a list of AI use cases related ESG. This list will be updated from time-to-time. 

• Predict ESG ratings using fundamental dataset: Investors (asset managers and asset owners) started to assess companies based on how they handle sustainability issues. To do this assessment, investors rely on specialized rating agencies that issue ratings along the environmental, social and governance (ESG) dimensions. Rating agencies base their analysis on subjective assessment of sustainability reports – which not every company provides. In order to alleviate these challenges, one or more AI / machine learning models can be used to predict ESG ratings using fundamental data.
• Predict environmental social and governance risk scores using sophisticated NLP techniques for classification tasks for ESG text using text retrieved from reports, disclosures, press releases, and 10-Q filings. Pre-trained BERT models can be used.
• Inclusion of environmental, social and governance (ESG) risk scores in models trained for stock portfolio optimization. Stock portfolio optimization is the process of continuous reallocation of funds to a selection of stocks. This is a particularly well-suited problem for reinforcement learning, as daily rewards are compounding and objective functions may include more than just profit, e.g., risk and sustainability.
• Impact of ESG related news articles and social media feeds on stock market performance

Conclusion

ESG and AI / machine learning can be used together in a number of ways. These use cases show how AI can be used to help identify companies that are at risk of violating ESG standards, companies that are not meeting their ESG goals, and companies that are making positive progress on their ESG goals.