ESGシグナルの予測・活用・評価：サステナブルファイナンスにおける機械学習の三分類体系レビュー
Predicting, Using, and Assessing ESG Signals: A Tripartite Systematic Review of Machine Learning in Sustainable Finance (原題)
(著者不明)
🤖 gxceed AI 要約
日本語
ESG格付の方法論的不透明性・格付乖離・グリーンウォッシュを背景に、ML/DL/NLP/XAIがESG評価をどう変容させるかをPRISMA準拠で127研究をレビュー。ESGスコアの機能的役割を「予測(29)」「活用(57)」「評価(41)」に三分類し、評価系研究をXAIによる格付関数の逆解析、乖離調整、グリーンウォッシュ検出、業種マテリアリティのクラスタリングの4クラスタに整理。格付は低コストの願望的開示を過大評価し、パフォーマンス証拠を軽視する傾向があり、グリーンウォッシュリスクを高めうると指摘する。
English
A PRISMA-guided review of 127 studies on how ML, DL, NLP, and XAI are transforming ESG rating analysis. It proposes a tripartite framework classifying ESG scores as predicted (29), used (57), or assessed (41), and is the first synthesis of the assessment stream: XAI reverse-engineering of proprietary scoring, divergence reconciliation, greenwashing detection, and industry-materiality clustering. Evidence suggests ratings over-weight low-cost aspirational disclosure versus costly performance evidence, raising greenwashing risk. Extreme fit statistics often stem from target-proximal or non-temporal validation, cautioning against reading high R2 as transferable forecasting.
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
SSBJ基準・有報でのサステナビリティ開示が進む日本では、ESG格付の信頼性・格付乖離への対応が投資家・企業双方の課題。本レビューはXAIによる格付検証やグリーンウォッシュ検出の手法群を整理し、日本企業の開示が格付でどう評価されるかを理解する枠組みを提供する。
In the global GX context
Amid ISSB/CSRD/SEC climate disclosure and growing reliance on ESG ratings for capital allocation, this review maps how ML/XAI can verify rating construction, reconcile divergence, and detect greenwashing. It directly informs global debates on rating credibility, regulatory oversight of ESG data providers, and the limits of predictive validation in sustainable finance.
👥 読者別の含意
🔬研究者:ESG格付・グリーンウォッシュ研究におけるML手法の分類枠組みと検証上の落とし穴（時系列外検証の欠如）を提供する。
🏢実務担当者:自社の開示が格付でどう重み付けされるか、願望的開示偏重のリスクを理解し、開示戦略の見直しに活用できる。
🏛政策担当者:ESG格付プロバイダー規制やグリーンウォッシュ対策を検討する際、ML/XAIによる検証手法と限界を参照できる。
📄 Abstract（原文）
Environmental, Social, and Governance (ESG) ratings increasingly shape capital allocation, corporate strategy, and regulatory oversight, yet their credibility is constrained by methodological opacity, rating divergence, and greenwashing risk. Prior reviews treat machine learning (ML) in ESG as a prediction problem. We identify an emerging research trajectory in which ML is increasingly used not only to consume ESG signals but also to verify their construction and credibility. Drawing on signaling theory, we conduct a PRISMA-guided systematic review of 127 peer-reviewed studies from Scopus and Web of Science to examine how machine learning (ML), deep learning (DL), Natural Language Processing (NLP), and Explainable AI (XAI) are transforming ESG rating analysis. We develop a tripartite framework classifying studies by the functional role of the ESG score: predicted (n = 29), used (n = 57), or assessed (n = 41). Our central contribution is the first synthesis of the methodological-assessment stream, organized into four clusters: XAI reverse-engineering of proprietary scoring functions, divergence reconciliation, greenwashing detection, and unsupervised industry-materiality clustering. The evidence assembled in this stream indicates that ESG ratings weight low-cost aspirational disclosure heavily relative to costly performance evidence, suggesting that greater reliance on aspirational disclosure relative to performance evidence may increase greenwashing risk, consistent with signaling-theory concerns. A study-level validation appraisal further shows that the most extreme fit statistics often arise in target-proximal reconstruction or non-temporal validation settings, cautioning against interpreting high R2 as evidence of transferable out-of-time forecasting.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.3390/jrfm19090708first seen 2026-09-12 05:35:11 · last seen 2026-09-21 05:08:07
🔔 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。