Development of Machine Learning Methods to Improve ESG Scores and Responsible Investment Decisions

The Principles for Responsible Investment (PRI) provide a framework for improving the analysis of environmental, social and governance issues (ESG) in the investment process and help companies exercise responsible practices in managing their investments. However, there is not yet a methodological standard for measuring ESG performance. The information necessary to understand the ESG impact of a company is in an unstructured relational format and artificial intelligence can be used in these efforts. We propose to develop a rating framework to automatically extract relevant ESG information from companies’ disclosures using Natural Language Processing (NLP) methods. In general, machine learning methodologies will be used to analyze the ESG performance of projects, companies or investment/debt portfolios. There is not yet a transparent relationship between ESG and financial data. In order to better understand the compromise between ESG factors and a pure risk/return optimum, we will explore the
use of knowledge graphs to create a model for both financial and non-financial data interactions. Clearly, explainability and transparency will be primal concerns in our development. This project is well established as an internal line of research at Axionable. It is aligned with Axionable's mission of assisting companies to gain business value in a sustainable market.

Intern: 
Elham Kheradmand
Superviseur universitaire: 
Manuel Morales
Province: 
Quebec
Partenaire: 
Partner University: