ESG score prediction through random forest algorithm

Valeria D’Amato (), Rita D’Ecclesia and Susanna Levantesi
Additional contact information
Valeria D’Amato: University of Salerno
Rita D’Ecclesia: Sapienza University of Rome
Susanna Levantesi: Sapienza University of Rome

Computational Management Science, 2022, vol. 19, issue 2, No 8, 347-373

Abstract: Abstract Environment-related risks affect assets in various sectors of the global economy, as well as social and governance aspects, giving birth to what is known as ESG investments. Sustainable and responsible finance has become a major aim for asset managers who are regularly dealing with the measurement and management of ESG risks. To this purpose, Financial Institutions and Rating Agencies have created an ESG score aimed to provide disclosure on the environment, social, and governance (corporate social responsibilities) metrics. CSR/ESG ratings are becoming quite popular even if highly questioned in terms of reliability. Asset managers do not always believe that markets consistently and correctly price climate risks into company valuations, in these cases ESG ratings, when available, provide an important tool in the company’s fundraising process or on the shares’ return. Assuming we can choose a reliable set of CSR/ESG ratings, we aim to assess how structural data- balance sheet items- may affect ESG scores assigned to regularly traded stocks. Using a Random Forest algorithm, we investigate how structural data affect the Thomson Reuters Refinitiv ESG scores for the companies which constitute the STOXX 600 Index. We find that balance sheet data provide a crucial element to explain ESG scores.

Keywords: Machine Learning; ESG risks; Firm performance; G14; C22 (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (7)

Downloads: (external link)
http://link.springer.com/10.1007/s10287-021-00419-3 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:comgts:v:19:y:2022:i:2:d:10.1007_s10287-021-00419-3

Ordering information: This journal article can be ordered from
http://www.springer. ... ch/journal/10287/PS2

DOI: 10.1007/s10287-021-00419-3

Access Statistics for this article

Computational Management Science is currently edited by Ruediger Schultz

More articles in Computational Management Science from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().