Pierre Steve Raymond

Outputs

Development of machine learning models to improve ESG scores and responsible investment decisions

Asset managers and financial institutions are increasingly relying on ESG rating agencies to assess, measure, and compare the Environmental, Social, and Governance (ESG) performance of companies. However, there is not yet a methodological standard for measuring ESG performance. The information necessary to understand the ESG impact of a company is contained in an unstructured format. The goal of this project is to structure the volume of ESG data. We develop a python script to extract the text, tables, and images from financial reports, SEC filings (10-k, 10-Q, …), sustainability reports, media reports, the news, social media and also, collect publicly available data from companies’ website related to ESG in addition to ESG news. The script will tag, label, and categorize companie’s information, the companies’ disclosures and the ESG news by characteristics such as industry sector, market cap, earnings, and date of issue to structure the data.