CNN-BiLSTMモデルと信号分解に基づく炭素市場ボラティリティとその応答メカニズム
Carbon Market Volatility and Its Response Mechanism Based on CNN-BiLSTM Model and Signal Decomposition (原題)
Yang Zhao
🤖 gxceed AI 要約
日本語
EU ETSを対象に、改良型bald eagle探索で最適化したVMD分解とCNN-BiLSTM・アテンションを組み合わせた炭素市場ボラティリティ予測フレームワークを提案。従来のGARCHモデルよりMAEで71%、RMSEで70%誤差を削減し、炭素デリバティブ価格評価や市場リスク管理への実用性を示した。
English
A hybrid framework combining improved bald eagle search-optimized VMD decomposition with CNN-BiLSTM and attention mechanisms is proposed to forecast carbon market volatility. Using EU ETS data, it cuts MAE by 71% and RMSE by 70% versus optimal GARCH models, offering a scalable path for carbon derivatives pricing and market risk management.
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推進機構によるカーボンクレジット市場や排出量取引制度の整備が進む中、炭素価格のボラティリティ予測は企業のカーボンリスク管理・調達戦略に直結する。EU ETSでの実証は日本の制度設計・価格リスク評価の参考になる。
In the global GX context
As carbon markets expand globally under Article 6 and compliance schemes, accurate volatility forecasting supports derivatives pricing, hedging, and market stability. The EU ETS empirical evidence offers transferable methodology for emerging carbon markets worldwide.
👥 読者別の含意
🔬研究者:深層学習と信号分解を組み合わせた炭素価格予測のベンチマークとして、GARCHとの比較設計が参考になる。
🏢実務担当者:炭素先物の価格変動リスク評価やヘッジ戦略の高度化に活用できる予測手法。
🏛政策担当者:排出量取引制度の価格安定性モニタリングや市場リスク監督の技術的示唆を提供する。
📄 Abstract（原文）
The carbon market volatility series exhibits strong nonlinearity, non-stationarity, and noise interference, which limits the accuracy of both traditional econometric models and standalone deep learning approaches. To address this, a hybrid prediction framework is developed. Firstly, an improved bald eagle search algorithm is adopted to optimize the hyperparameters of variational mode decomposition (VMD). Through chaos mapping initialization, dynamic inertia weight adjustment, and Gaussian mutation mechanism, population diversity and global search capability are enhanced, and the optimal number of VMD and penalty factor combination are obtained. Secondly, VMD is utilized to decompose the volatility series into several intrinsic modal components. Finally, bidirectional long short-term memory neural networks, convolutional neural networks, and attention mechanisms are introduced to achieve high-precision prediction of volatility series. The results using the EU Emissions Trading System as an empirical object show that traditional generalized autoregressive conditional heteroskedasticity (GARCH) models have limited performance in predicting carbon futures volatility. The optimal GARCH model has an R2 of 92.6779% and an average absolute percentage error of 9.8358%. The suggested model outperforms all traditional econometric models significantly in four evaluation indicators: The average absolute error is reduced by 71.19%, the root mean square error is reduced by 70.13%, the average absolute percentage error is reduced by 63.80%, and the R2 is enhanced by 6.11%. The designed framework provides a scalable technical path for predicting carbon market volatility and has practical application value for pricing carbon financial derivatives and market risk management.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.5755/j01.itc.55.3.45066first seen 2026-11-07 05:10:17
🔔 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。