Publication Type

Journal Article

Version

publishedVersion

Publication Date

5-2025

Abstract

Environmental, social and governance (ESG) factors have become key nonfinancial factors for investors to evaluate companies with respect to understanding material risks and growth opportunities. While not mandatory, companies are providing ESG reports that outline progress in different ESG metrics (six broad metrics and 15 specific ones). Client advisers (CAs) read these reports to identify key metrics of interest to investors. Given the number of companies and investment products, however, it is not feasible for CAs to read all the reports, which can sometimes run into tens or hundreds of pages). The authors have developed multiple frameworks building on leading approaches in natural language understanding (NLU) to identify relevant talking points in each document and then filter out the most important ones. A large bank has evaluated these approaches on a proprietary dataset of more than 100 sustainability reports and provided an F1 score of over 0.8. The system is currently being evaluated for integration into the bank’s decision-assist framework for client advisers.

Keywords

machine learning, natural language processing, investment products, client advisers, talking points

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems | Numerical Analysis and Scientific Computing

Research Areas

Intelligent Systems and Optimization

Publication

Journal of AI, Robotics & Workplace Automation

Volume

3

Issue

4

First Page

350

Last Page

361

ISSN

2633-562X

Identifier

10.69554/CMZB1679

Publisher

Henry Stewart

Embargo Period

8-25-2025

Additional URL

https://doi.org/10.69554/CMZB1679

Download

Share

COinS