Clustering S&P 500 companies by machine learning for sustainable decision-making

Ergenç Cansu () and Aktaş Rafet ()
Additional contact information
Ergenç Cansu: Ankara Yıldırım Beyazit University, Department of Business Administration, 06760, Ankara, Türkiye
Aktaş Rafet: Ankara Yıldırım Beyazit University, Department of Business Administration, 06760, Ankara, Türkiye

Economics and Business Review, 2025, vol. 11, issue 3, 91-118

Abstract: This study examines the Environmental, Social, and Governance (ESG) performance of S&P 500 companies using three clustering algorithms: K-Means, Gaussian Mixture Model, and Agglomerative Clustering. ESG scores from leading data providers are analysed to uncover sectoral patterns and performance trends. The findings indicate that technology and healthcare firms achieve the highest ESG scores, particularly in the governance and social dimensions, while the industrial and energy sectors face the greatest environmental challenges. Among the methods compared, K-Means demonstrates superior clustering performance by forming compact and well-separated ESG groups. These results offer a robust foundation for sector-specific ESG benchmarking, supporting investors and policymakers in identifying sustainability leaders, assessing risk, and targeting areas for improvement.

Keywords: sustainability; clustering algorithms; machine learning (search for similar items in EconPapers)
JEL-codes: Q01 Q56 Q57 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://doi.org/10.18559/ebr.2025.3.1895 (text/html)

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:vrs:ecobur:v:11:y:2025:i:3:p:91-118:n:1001

DOI: 10.18559/ebr.2025.3.1895

Access Statistics for this article

Economics and Business Review is currently edited by Tadeusz Kowalski

More articles in Economics and Business Review from Sciendo
Bibliographic data for series maintained by Peter Golla ().