CEEMDAN–FADE：炭素価格予測のためのデータ駆動型周波数適応アンサンブルフレームワーク
CEEMDAN–FADE: A Data-Driven Frequency-Adaptive Ensemble Framework for Carbon-Price Forecasting (原題)
Gui-Qiong Xu, Zhong-Qiang Gao, Yuan Liu
🤖 gxceed AI 要約
日本語
本研究は、信号分解・複雑度ベース再構成・データ駆動型モデル選択・動的重み付けを統合した周波数適応型アンサンブル枠組みCEEMDAN–FADEを構築し、炭素価格予測の精度向上を図る。中国の湖北・広東炭素市場での実証では、17のベンチマークモデルを大きく上回り、RMSEを最大46.24%削減した。予測に基づく取引分析でも収益性とリスク調整後性能の改善が確認され、実用性が示された。
English
This study builds CEEMDAN–FADE, a frequency-adaptive ensemble framework combining signal decomposition, complexity-based reconstruction, data-driven model selection, and dynamic weighting for carbon-price forecasting. In China's Hubei and Guangdong carbon markets, it outperforms 17 benchmarks, cutting RMSE by up to 46.24% with significant Diebold–Mariano tests. A forecast-based trading analysis shows improved profitability and risk-adjusted performance, indicating practical applicability.
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GXリーグやカーボンクレジット市場、東証の炭素関連商品の整備が進む中、炭素価格の予測精度は企業のリスク管理や投資判断に直結する。本手法は日本市場の価格データにも応用可能で、SSBJ開示における内部炭素価格設定の高度化にも示唆を与える。
In the global GX context
As carbon markets expand globally under Article 6 and compliance schemes, accurate price forecasting supports allowance trading, corporate risk management, and policy design. The framework's model-agnostic, frequency-adaptive design offers a transferable approach for other emerging carbon markets, complementing disclosure-focused research with quantitative market intelligence.
👥 読者別の含意
🔬研究者:炭素価格の非線形・多スケール性に対応するアンサンブル手法の設計と評価枠組みを提供する。
🏢実務担当者:炭素価格予測の精度向上により、排出量取引・リスク管理・内部炭素価格設定の意思決定を支援する。
🏛政策担当者:炭素市場の価格安定性や政策効果の評価に資する予測ツールとして参考になる。
📄 Abstract（原文）
Accurate and reliable carbon-price forecasts can provide scientific support for allowance trading, corporate risk management, and emission-reduction policymaking. However, carbon prices exhibit pronounced nonlinearity, nonstationarity, and multiscale dynamics, and existing studies mainly employ a single model uniformly for all decomposed components, with obvious limitations in matching model capability to component complexity and in adapting combination weights to changing market conditions. To fill these gaps, this study constructs CEEMDAN–FADE, a frequency-adaptive ensemble framework integrating signal decomposition, complexity-based reconstruction, data-driven model selection, and dynamic weighting. Specifically, CEEMDAN decomposition is followed by sample entropy-based K-means reconstruction, thus separating market noise from trend-driven movements. Subsequently, exogenous factors are screened for each reconstructed component, and the selected factors are used to configure component-specific inputs. Then, top-performing models are selected for each component from a heterogeneous pool of statistical, machine-learning, and deep-learning approaches according to validation performance, and combined through rolling dynamic weights estimated with Huber loss. Finally, empirical results in China’s Hubei and Guangdong carbon markets show that the proposed system significantly outperforms 17 benchmark models, reducing RMSE by 18.70% and 46.24% relative to the strongest benchmark, with Diebold–Mariano tests confirming significance. A forecast-based trading analysis further reveals improved profitability and risk-adjusted performance, indicating good robustness and practical applicability.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.3390/systems14101220first seen 2026-10-06 05:21:17
🔔 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。