Exploring the Impact of ESG Ratings on Corporate Carbon Emissions in Korean Firms: Evidence from Machine Learning and Deep Learning Models
韓国企業におけるESG評価が企業の炭素排出に与える影響：機械学習と深層学習モデルの証拠 (AI 翻訳)
C. Kim, H. Na
🤖 gxceed AI 要約
日本語
本研究は韓国企業を対象に、ESG評価データを用いたAIベースの排出量予測モデルを開発。機械学習と深層学習を比較し、CatBoost・GAN・Transformerのハイブリッドアンサンブルが最高性能を示した。ESG情報が排出量予測に有用であることを実証。
English
This study develops an AI-based screening framework using ESG ratings to predict corporate carbon emissions among Korean KOSPI-listed firms. Comparing ML and DL models, a hybrid ensemble of CatBoost, GAN, and Transformer outperforms individual models. ESG information significantly improves prediction accuracy, offering a tool for compliance monitoring under the K-ETS.
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
日本でもGX-ETSやSSBJ開示が進む中、AIを活用した排出量スクリーニング手法は投資家や規制当局にとって有用。韓国K-ETSを対象とするが、日本の排出量取引制度や有報開示にも応用可能。
In the global GX context
As carbon pricing expands globally, AI-based screening tools like this hybrid ensemble can help regulators and investors identify high-emitting firms. While focused on Korea, the methodology is transferable to other jurisdictions with mandatory emissions reporting, such as the EU ETS or emerging carbon markets.
👥 読者別の含意
🔬研究者:Demonstrates the incremental value of ESG features in emission prediction and compares advanced ML/DL models on a regulatory threshold task.
🏢実務担当者:Provides a practical AI framework for compliance-oriented screening to anticipate inclusion in emissions trading schemes and manage transition risk.
🏛政策担当者:Offers a decision support tool for monitoring and enforcing emission reduction targets under carbon pricing mechanisms like K-ETS.
📄 Abstract（原文）
This study examines corporate carbon emissions of Korean firms from an ESG perspective and develops an AI-based screening framework to improve the identification of firms likely to exceed regulatory emission thresholds. As global climate policies and carbon pricing mechanisms expand, understanding the emission profiles of listed companies has become increasingly important for regulators, investors, and policymakers. Despite growing ESG disclosure, reliable firm-level screening tools for carbon emissions remain limited. Using a pooled annual panel of KOSPI-listed non-financial firms from 2019 to 2024, the study constructs a dataset of 552 firm-year observations. Firms are classified as high-emission when annual emissions exceed the Korean Emissions Trading Scheme (K-ETS) regulatory threshold of 125,000 tCO2e. To evaluate predictive performance, the analysis compares multiple machine learning models (RF, SVM, XGBoost, LightGBM, and CatBoost) and deep learning models (CNN, RNN, GAN, LSTM, and Transformer). In addition, a hybrid ensemble combining CatBoost, GAN, and Transformer is proposed to enhance predictive reliability. The empirical results show that ESG-augmented models consistently outperform financial-only baselines across AUC and F1 metrics. Among individual models, the ESG-enhanced Transformer achieves the strongest discriminatory power, while the proposed hybrid ensemble delivers the best overall predictive performance. The findings contribute to the literature by demonstrating the incremental value of ESG information in predicting corporate carbon emissions and by presenting a practical AI-based framework for compliance-oriented screening under carbon regulation. From a policy and investment perspective, the model provides a useful decision support tool for anticipating potential inclusion in emissions trading schemes, assessing transition exposure, and supporting data-driven decarbonization strategies.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.3390/su18094553first seen 2026-05-15 17:02:15
🔔 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。