Financial Risk Prediction Models Integrating Environmental, Social and Governance Factors: A Systematic Review
環境・社会・ガバナンス（ESG）要素を統合した金融リスク予測モデル：系統的レビュー (AI 翻訳)
Cristina Caro-González, Daniel Jato-Espino, Yudith Cardinale
🤖 gxceed AI 要約
日本語
本系統的レビューは、ESG要素を金融リスク予測に統合する研究を64編分析。従来の計量経済学手法が48%を占める一方、機械学習（ML）39%、自然言語処理（NLP）8%とAI手法の活用が進む。ML（アンサンブル法、ニューラルネットワーク）は信用リスク予測精度を向上、NLPは非構造化ESG開示分析に有望。中国、イタリア、米国、インドで研究が集中し、データ不整合や新興市場の不足が課題。
English
This systematic review of 64 studies on integrating ESG factors into financial risk prediction finds that traditional econometrics still dominate (48%), but ML (39%), NLP (8%) are growing. ML models, especially ensemble methods and neural networks, improve credit risk and default prediction; NLP shows promise for analyzing unstructured ESG disclosures. Research is concentrated in China, Italy, the US, and India, with persistent challenges in data inconsistency, rating variability, and coverage of emerging markets.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本ではSSBJ基準や有価証券報告書におけるESG情報開示が進み、AIを用いたリスク評価モデルの重要性が高まる。本レビューは、日本の金融機関や企業がESGデータを信用リスク予測に活用する際の方法論的指針とデータ整備の方向性を示す。
In the global GX context
With TCFD, ISSB, CSRD, and SEC climate disclosure rules, ESG factors are increasingly integrated into financial risk models. This systematic review provides a global landscape of AI/ML approaches for ESG-risk modeling, highlighting methodological trends, data challenges, and the gap between research and practice, relevant for standard-setters and risk managers.
👥 読者別の含意
🔬研究者:Provides a comprehensive taxonomy of methodologies (ML, NLP, LLM) and identifies key gaps like emerging market coverage and data inconsistency.
🏢実務担当者:Offers insights on which ML models (ensemble, neural nets) improve credit risk prediction using ESG data, useful for building internal risk models.
🏛政策担当者:Highlights the need for standardized ESG data and consistent ratings to enable effective integration into financial risk models.
📄 Abstract（原文）
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.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://www.mdpi.com/2227-7072/14/2/31/pdf?version=1770081655first seen 2026-07-18 08:26:35
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。