No open-access location is known for this record yet.
No open-access location is known for this record yet.
ABSTRACT The integration of machine learning into environmental, social, and governance (ESG) research has gained significant traction, offering advanced predictive capabilities, enhanced decision‐making, and improved transparency in sustainable finance. Despite a growing body of literature, no systematic effort has been made to comprehensively map the intersection of ESG and machine learning. This study conducts a systematic literature review, synthesizing insights from 57 high‐quality articles published between 2004 and 2024 on the Web of Science and Scopus. Employing bibliometric analysis, thematic analysis, and the TCCM framework, this study identifies dominant research themes, methodological advancements, and persistent gaps in ESG‐machine learning literature. Findings reveal the increasing application of machine learning in ESG score prediction, risk assessment, investment decision‐making, and controversy detection while highlighting key challenges such as data standardization, model explainability, and algorithmic bias. Random Forest consistently demonstrated the highest prediction accuracy across several studies. This study offers valuable implications for academics, practitioners, and policymakers, providing a structured foundation for advancing ESG analytics and fostering responsible artificial intelligence‐driven sustainability strategies.
Loading…
Stored only when both papers are in the corpus — 34 citations exist upstream.
Papers that cite the same references — the relational fallback while embeddings are still backfilling.
Imported from OpenAlex (CC0) — nothing here is generated.