Financial Risk Prediction Models Integrating Environmental, Social and Governance Factors: A Systematic Review

This systematic review explores the incorporation of Environmental, Social, and Governance (ESG) factors within financial risk prediction models, with a particular focus on Machine Learning (ML), Natural Language Processing (NLP), and Large Language Models (LLM). Adhering to the Preferred Reporting Items for Systematic Reviews and the Meta-Analyses (PRISMA) and PICOC frameworks, we identified 74 peer-reviewed publications disseminated between 2009 and March 2025 from the Scopus database. After excluding 10 systematic and literature reviews to avoid double-counting of evidence, we conducted quantitative analysis on 64 empirical studies. The findings indicate that traditional econometric methodologies continue to prevail (48%), followed by ML strategies (39%), NLP methodologies (8%), and Other (5%). Research that concurrently focuses on all three dimensions of ESG constitutes the most substantial category (44%), whereas the Social dimension, in isolation, receives minimal focus (5%). A geographic analysis reveals a concentration of research activity in China (13 studies), Italy (10), and the United States and India (6 each). Chi-square tests reveal no statistically significant relationship between the methodological approaches employed and the ESG dimensions examined (p = 0.62). The principal findings indicate that ML models—particularly ensemble methodologies and neural networks—exhibit enhanced predictive accuracy in the context of credit risk and default probability, whereas NLP methodologies reveal significant potential for the analysis of unstructured ESG disclosures. The review highlighted ongoing challenges, including inconsistencies in ESG data, variability in ratings across different providers, insufficient coverage of emerging markets, and the disparity between academic research and practical application in model implementation.