Are Industry Sectors Critical for ESG Score Prediction? Evidence From the U.S. Manufacturing and Service Sectors Using Machine Learning Methods
業種セクターはESGスコア予測に重要か？機械学習手法を用いた米国製造業およびサービス業からの証拠 (AI 翻訳)
Tanzina Hossain, Mahfuja Malik, K. S. M. Tozammel Hossain, Sarah Ryan
🤖 gxceed AI 要約
日本語
本研究は、米国の製造業とサービス業の2業種を対象に、10種類の機械学習アルゴリズムを用いてESGスコアを予測する。結果、製造業の方がサービス業よりもESGスコアの予測が容易であり、製造業ではXGBoostが、サービス業ではランダムフォレストが最も効果的だった。また、GDP、企業規模、レバレッジが重要因子であることが示された。
English
This study predicts ESG scores for U.S. manufacturing and service sectors using ten machine learning algorithms. Results show ESG scores are more predictable in manufacturing than services, with XGBoost best for manufacturing and Random Forest for services. Key drivers include GDP, firm size, and leverage, with causal effects identified.
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
日本企業にとっても、業種別にESG予測モデルを構築する重要性を示唆する。特に製造業とサービス業で特性が異なることは、国内でのESG評価戦略に応用可能。
In the global GX context
This paper adds industry-specific evidence to global ESG prediction literature, demonstrating that ML approaches need tailoring by sector. While U.S.-focused, the methodology is transferable to other markets including Japan.
👥 読者別の含意
🔬研究者:Demonstrates that ML prediction of ESG scores varies significantly by industry, suggesting the need for sector-specific models.
🏢実務担当者:Provides evidence that manufacturing firms can more reliably predict ESG scores using ML, helping prioritize resource allocation for disclosure improvement.
📄 Abstract（原文）
ABSTRACT Environmental, social, and governance (ESG) ratings reflect a company's sustainability practices and support decision‐making, yet research often overlooks industry‐specific analysis, limiting cross‐sector insights. This study aims to predict industry‐specific ESG scores by applying ten machine learning algorithms to two U.S. industries: manufacturing and services. Results show that ESG scores are more predictable in manufacturing than in services. Of the tested algorithms, the extreme gradient boosting regressor is most effective for manufacturing, while the random forest regressor performed best in services. We employ mean decrease in impurity, permutation importance and double machine learning to identify key drivers. In manufacturing, GDP, firm size, and leverage are consistently important, with unemployment showing a strong causal effect, while service‐sector results are more heterogeneous, reflecting greater complexity. This combined approach of predictive and causal analysis offers valuable industry‐specific insights, advancing understanding of ESG prediction and highlighting the need for tailored strategies for different sectors.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.1002/jcaf.70052first seen 2026-07-18 06:44:55
🔔 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。