A Design Science Approach to Predicting ESG Performance Using Ensemble Machine Learning
アンサンブル機械学習を用いたESGパフォーマンス予測へのデザインサイエンスアプローチ (AI 翻訳)
Yara Ibrahim, Khaled Hussainey, Taghred Moukhtar Sayed Moawad
🤖 gxceed AI 要約
日本語
本研究はデザインサイエンスパラダイムに基づき、アンサンブル機械学習を用いたESG予測フレームワークを開発。RefinitivとBloombergの企業データを用い、ESGパフォーマンスは中程度予測可能であり、アンサンブル手法が深層学習を上回ることを示した。開示の頑健性は予測が困難で、データ品質とモデル選択の重要性を強調。
English
This study develops an ESG prediction framework using ensemble machine learning under the Design Science paradigm. Using Refinitiv and Bloomberg firm-level data, it finds ESG performance moderately forecastable, with ensemble methods outperforming deep learning, while disclosure robustness is less predictable, highlighting data quality and model selection.
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開示基準や有報におけるESG情報の充実が進んでいます。本論文はESGスコア予測可能性を実証し、開示の質と予測モデルの選択が重要であることを示しており、日本の企業や投資家にとって実践的な示唆を与えます。
In the global GX context
Globally, this study informs the ongoing discourse on ESG data quality, model interpretability (XAI), and the predictability of both composite ESG scores and disclosure robustness, relevant for ISSB and CSRD implementation.
👥 読者別の含意
🔬研究者:Provides a robust methodological framework for ESG prediction and highlights limitations of deep learning in tabular data.
🏢実務担当者:Offers insights on model selection and data quality for ESG analytics in corporate sustainability teams.
🏛政策担当者:Emphasizes the need for standardized data to reduce disclosure bias and improve predictability.
📄 Abstract（原文）
Environmental, Social, and Governance (ESG) metrics have become a cornerstone to sustainable finance, yet their measurement and predictability remain constrained by data heterogeneity, methodological divergence, and disclosure bias. This study develops a comprehensive ESG prediction framework grounded in the Design Science Research paradigm, integrating advanced machine learning techniques with rigorous data preprocessing, feature selection, and temporal validation. Using firm-level data from Refinitiv and Bloomberg, the analysis distinguishes between ESG composite performance and disclosure-based robustness, addressing a critical gap in the literature. Ensemble learning models, including Random Forest and XGBoost, are evaluated alongside deep learning architectures using multiple sampling strategies and rolling-window validation. The results demonstrate that ESG performance is moderately forecastable, with ensemble methods consistently outperforming neural networks in structured datasets. In contrast, disclosure robustness exhibits lower predictability, reflecting its dependence on discretionary strategic reporting and institutional factors. The findings highlight the importance of data quality, model selection, and validation design in ESG analytics, while emphasizing the limitations of deep learning in tabular financial contexts. The integration of explainable artificial intelligence further enhances interpretability by identifying key predictors of ESG outcomes. Overall, the study contributes to the literature by providing a robust, interpretable, and methodologically rigorous framework for ESG prediction, with implications for investors, regulators, and corporate decision-making.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.3390/ijfs14050133first seen 2026-05-23 05:47:50 · last seen 2026-05-27 05:00:58
🔔 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。