EvoGame-CAKNet: Integrating Evolutionary Game Theory and Multi-Head Contextual Attention Augmented Kolmogorov Arnold Networks for Accurate Carbon Price Forecasting
EvoGame-CAKNet：進化ゲーム理論とマルチヘッド文脈注意機構を統合したKolモゴロフ-アーノルドネットワークによる高精度炭素価格予測 (AI 翻訳)
Yufei Xi, Jiangzhang Zhu, Peng Wang, Mingfang He
🤖 gxceed AI 要約
日本語
炭素価格予測のための新しいハイブリッドフレームワークEvoGame-CAKNetを提案。進化ゲーム理論で市場参加者の戦略をモデル化し、マルチヘッド注意機構とKANを用いて高次元データの非線形関係を学習。中国4市場での実験でMAPEを18.3～31.6%削減した。
English
Proposes EvoGame-CAKNet, a hybrid framework for carbon price forecasting integrating evolutionary game theory to model multi-agent strategies, multi-head contextual attention for long-range dependencies, and Kolmogorov-Arnold networks for nonlinear fitting under small samples. Experiments on four Chinese carbon markets show superior performance with 18.3-31.6% MAPE reduction.
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
日本の排出量取引制度（GXリーグ等）でも価格予測は重要だが、本論文は中国市場に特化。ただし、手法は日本市場への応用可能性があり、SSBJ開示における価格リスク分析にも示唆を与える。
In the global GX context
Contributes to global carbon price forecasting literature using AI, relevant for emission trading schemes worldwide. While focused on China, the methodology could be adapted for EU ETS, California cap-and-trade, or other markets, supporting transition finance and carbon risk management.
👥 読者別の含意
🔬研究者:Provides a novel hybrid model (EGT+attention+KAN) for carbon price forecasting, outperforming existing baselines.
🏢実務担当者:Offers a practical tool for carbon market participants to improve price predictions and inform trading strategies.
🏛政策担当者:Demonstrates how AI can enhance carbon market efficiency, relevant for designing and adjusting emission trading schemes.
📄 Abstract（原文）
Accurate carbon price for ecasting is crucial for the management of emission trading schemes and the formulation of low-carbon policies. However, existing models face three intertwined challenges: the interdependent multi-agent strategies among market participants, the long-term time dependence of high-dimensional environmental and economic covariates, and the severe nonlinearity under the constraint of small samples. This paper proposes the novel hybrid framework EvoGame-CAKNet. Firstly, an evolutionary game theory (EGT) is proposed to simulate the evolution of dynamic strategies of different market participants (enterprises, regulatory agencies, financial institutions), and policy effect signals are embedded as structured prior information. Secondly, a knowledge network (CAKNet) combining multi-head context attention is designed for adaptive long-distance feature aggregation across climate, macroeconomy, and policy dimensions. Finally, a Kolmogorov–Arnold network (KAN) is proposed to replace the traditional multi-layer perceptron decoder, using learnable unary activation functions to achieve better nonlinear fitting under data scarcity conditions. Experiments on four major carbon markets in Beijing, Shanghai, Hubei, and Guangdong from 2014 to 2023 show that EvoGame-CAKNet achieves the most advanced performance, with an average absolute percentage error (MAPE) reduced by 18.3% to 31.6% compared to the best base model. Abandonment studies confirm that each component works collaboratively, with the prior knowledge of EGT having the most significant impact during the regulatory transition period. CAKNet not only provides theoretical progress in multi-agent market modeling but also offers practical decision support for stakeholders in the carbon market.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.3390/math14142487first seen 2026-07-14 04:48:27
- semanticscholar https://doi.org/10.3390/math14142487first seen 2026-07-14 04:59:55
🔔 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。