gxceed
← 論文一覧に戻る

Using Machine Learning to Detect Financial Distress From Sustainability Reports

機械学習を用いたサステナビリティ報告書からの財務危機検出 (AI 翻訳)

Songshan Qin, Mohamed Bakoush, Frank McGroarty

Business Strategy and the Environment📚 査読済 / ジャーナル2026-01-16#ESGOrigin: US
DOI: 10.1002/bse.70563
原典: https://doi.org/10.1002/bse.70563

🤖 gxceed AI 要約

日本語

本研究は、サステナビリティ報告書のテキストデータをNLPで解析し、財務危機予測モデルの精度向上を検証。S&P500企業の1220報告書を用い、Random ForestやXGBoostが高い性能を示した。ESG項目の重要性はセクターによって異なる。

English

This study uses NLP on 1,220 sustainability reports from S&P 500 firms (2018-2022) to predict financial distress. Incorporating textual ESG disclosures significantly improves model accuracy over quantitative-only models, with Random Forest and XGBoost performing best. Materiality of ESG issues varies by sector.

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

日本企業にとって、サステナビリティ報告が信用リスク評価に有用であることを示す。SSBJ基準等の開示データを活用した新たなリスク分析手法の可能性を示唆。

In the global GX context

Demonstrates the predictive value of sustainability disclosures for credit risk, aligning with global trends in integrating ESG into financial analysis. Offers a framework applicable under ISSB or SEC climate disclosure rules.

👥 読者別の含意

🔬研究者:Provides a novel approach to link textual ESG disclosures with financial distress prediction using ensemble learning.

🏢実務担当者:Credit analysts can leverage sustainability report text to enhance default risk models.

📄 Abstract（原文）

This study examines the incremental predictive value of sustainability reports in forecasting corporate financial distress. We first construct a unique sample of 1220 sustainability reports produced by 244 firms from S&P 500 index between 2018 and 2022. We then employ natural language processing (NLP) techniques to extract key features from the textual content of corporate sustainability reports, introducing them as a novel input to financial distress prediction models. A suite of machine learning algorithms is then applied to assess predictive performance. Our results show that incorporating textual sustainability disclosures significantly improves model performance relative to using only quantitative variables. These textual reports outline the corporate strategies on sustainability, providing additional insights that enhance the prediction of financial distress. Among the tested models, Random Forest and XGBoost regressors exhibit superior performance. We also find that the materiality of specific ESG issues in predicting financial distress varies across sectors. Overall, this study offers a framework for integrating sustainability reports and ensemble learning into corporate credit risk assessment.

🔗 Provenance — このレコードを発見したソース

🔔 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。