曖昧環境下でのXGBoostと構造学習（SLAVE）を用いた商業銀行のESG要因による信用リスク予測
Predicting Credit Risk with ESG Factors Using XGBoost and Structural Learning in Vague Environments (SLAVE) in Commercial Banks (原題)
Jamil J. Jaber, A. A. Alkhawaldeh, Qusay Ayman Sulayman Mazahreh, Ala’Aldin Al Rowwad, Anwar Al-Gasaymeh, T. Kaddumi
🤖 gxceed AI 要約
日本語
本研究は、中東7カ国の商業銀行40行のパネルデータ（2014-2023年）を用いて、機械学習（XGBoost）とファジィルールベースモデル（SLAVE）を組み合わせ、ESGスコアを含む要因で信用リスクを予測する。回帰分析では収益性とESGスコアが信用リスクを有意に低下させ、SHAP分析ではESGスコアが最も影響力のある予測因子と判明。SLAVEモデルは80/20分割で最高精度を達成し、低リスク銀行の識別に優れる。持続可能な銀行業務と信用リスク低減へのESGの重要性を示す。
English
This study predicts credit risk in commercial banks using machine learning (XGBoost) and a fuzzy rule-based model (SLAVE) on panel data from 40 banks across seven Middle Eastern countries (2014-2023). Regression results show profitability and ESG score significantly reduce credit risk, while SHAP analysis identifies ESG score as the most influential predictor. The SLAVE model achieves highest accuracy with an 80/20 split, excelling in identifying low-risk banks. Findings highlight ESG's role in fostering sustainable banking and reducing credit risk.
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開示や金融機関の気候変動対応が進む中、ESGスコアを信用リスク評価に組み込む手法は、地域金融機関やメガバンクの与信判断に示唆を与える。AI活用によるESGデータの統合は、今後の開示実務やリスク管理の高度化に寄与する可能性がある。
In the global GX context
Globally, this paper contributes to the growing literature on ESG-integrated credit risk assessment, aligning with regulatory trends like Basel III and sustainable finance initiatives. The use of XGBoost and SHAP offers a replicable methodology for banks worldwide to incorporate ESG factors into risk frameworks, supporting the transition to sustainable banking.
👥 読者別の含意
🔬研究者:Provides empirical evidence on ESG's predictive power for credit risk in emerging markets, with a novel combination of XGBoost and SLAVE.
🏢実務担当者:Offers a data-driven approach for integrating ESG scores into credit risk models, potentially improving loan pricing and portfolio management.
🏛政策担当者:Highlights the value of ESG data in financial stability, suggesting regulatory support for standardized ESG reporting.
📄 Abstract（原文）
Predicting credit risk is vital for banks as it safeguards financial stability, minimizes default losses, optimizes capital, and ensures regulatory compliance. This study aims to predict credit risk (High/Low) in commercial banks by integrating machine learning with traditional econometric approaches. The Structural Learning in Vague Environments (SLAVE) fuzzy rule-based model handles ambiguity in financial decisions, while the eXtreme Gradient Boosting (XGBoost) uncovers non-linear patterns among predictors. Input variables—profitability, liquidity risk, ESG (environmental, social, and governance) score, and monetary freedom—were selected via multicollinearity tests and three panel regression models, including ordinary least squares (OLS), fixed effects, and random effects models. The empirical investigation uses a panel dataset of forty commercial banks across seven Middle Eastern countries from 2014 to 2023, yielding 400 observations. Regression results reveal that profitability and ESG score significantly reduce credit risk. Liquidity risk and monetary freedom increase credit risk. XGBoost combined with the SHapley Additive exPlanations (SHAP)-based interpretation identifies ESG Score as the most influential predictor. The SLAVE model was evaluated using three data splits: 70/30, 80/20, and 90/10. The 80/20 split achieved the highest accuracy, with superior performance in identifying low-risk banks. Stronger ESG performance and stable monetary environments contribute to fostering sustainable banking and reducing credit risk, making these indicators valuable for risk management frameworks in the Middle Eastern banking sector.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.3390/risks14090194first seen 2026-09-02 05:44:01 · last seen 2026-09-11 05:52:04
🔔 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。