Multifractal Carbon Market Price Forecasting with Memory-Guided Adversarial Network
Carbon market price prediction is critical for stabilizing markets and advancing low-carbon transitions, where capturing multifractal dynamics is essential. Traditional models often neglect the inherent long-term memory and nonlinear dependencies of carbon price series. To tackle the issues of nonli...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Fractal and Fractional |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-3110/9/7/403 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849303513098616832 |
|---|---|
| author | Na Li Mingzhu Tang Jingwen Deng Liran Wei Xinpeng Zhou |
| author_facet | Na Li Mingzhu Tang Jingwen Deng Liran Wei Xinpeng Zhou |
| author_sort | Na Li |
| collection | DOAJ |
| description | Carbon market price prediction is critical for stabilizing markets and advancing low-carbon transitions, where capturing multifractal dynamics is essential. Traditional models often neglect the inherent long-term memory and nonlinear dependencies of carbon price series. To tackle the issues of nonlinear dynamics, non-stationary characteristics, and inadequate suppression of modal aliasing in existing models, this study proposes an integrated prediction framework based on the coupling of gradient-sensitive time-series adversarial training and dynamic residual correction. A novel gradient significance-driven local adversarial training strategy enhances immunity to volatility through time step-specific perturbations while preserving structural integrity. The GSLAN-BiLSTM architecture dynamically recalibrates historical–current information fusion via memory-guided attention gating, mitigating prediction lag during abrupt price shifts. A “decomposition–prediction–correction” residual compensation system further decomposes base model errors via wavelet packet decomposition (WPD), with ARIMA-driven dynamic weighting enabling bias correction. Empirical validation using China’s carbon market high-frequency data demonstrates superior performance across key metrics. This framework extends beyond advancing carbon price forecasting by successfully generalizing its “multiscale decomposition, adversarial robustness enhancement, and residual dynamic compensation” paradigm to complex financial time-series prediction. |
| format | Article |
| id | doaj-art-8d0411274c574ddebee9fb2f2d75549f |
| institution | Kabale University |
| issn | 2504-3110 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Fractal and Fractional |
| spelling | doaj-art-8d0411274c574ddebee9fb2f2d75549f2025-08-20T03:58:26ZengMDPI AGFractal and Fractional2504-31102025-06-019740310.3390/fractalfract9070403Multifractal Carbon Market Price Forecasting with Memory-Guided Adversarial NetworkNa Li0Mingzhu Tang1Jingwen Deng2Liran Wei3Xinpeng Zhou4School of Economics & Management, Changsha University of Science & Technology, Changsha 410114, ChinaSchool of Energy and Power Engineering, Changsha University of Science & Technology, Changsha 410114, ChinaSchool of Computer Science and Technology, Changsha University of Science & Technology, Changsha 410114, ChinaSchool of Computer Science and Technology, Changsha University of Science & Technology, Changsha 410114, ChinaSchool of Computer Science and Technology, Changsha University of Science & Technology, Changsha 410114, ChinaCarbon market price prediction is critical for stabilizing markets and advancing low-carbon transitions, where capturing multifractal dynamics is essential. Traditional models often neglect the inherent long-term memory and nonlinear dependencies of carbon price series. To tackle the issues of nonlinear dynamics, non-stationary characteristics, and inadequate suppression of modal aliasing in existing models, this study proposes an integrated prediction framework based on the coupling of gradient-sensitive time-series adversarial training and dynamic residual correction. A novel gradient significance-driven local adversarial training strategy enhances immunity to volatility through time step-specific perturbations while preserving structural integrity. The GSLAN-BiLSTM architecture dynamically recalibrates historical–current information fusion via memory-guided attention gating, mitigating prediction lag during abrupt price shifts. A “decomposition–prediction–correction” residual compensation system further decomposes base model errors via wavelet packet decomposition (WPD), with ARIMA-driven dynamic weighting enabling bias correction. Empirical validation using China’s carbon market high-frequency data demonstrates superior performance across key metrics. This framework extends beyond advancing carbon price forecasting by successfully generalizing its “multiscale decomposition, adversarial robustness enhancement, and residual dynamic compensation” paradigm to complex financial time-series prediction.https://www.mdpi.com/2504-3110/9/7/403carbon market price predictionmultifractal analysisadversarial robustnesswavelet packet decompositionmarket efficiency |
| spellingShingle | Na Li Mingzhu Tang Jingwen Deng Liran Wei Xinpeng Zhou Multifractal Carbon Market Price Forecasting with Memory-Guided Adversarial Network Fractal and Fractional carbon market price prediction multifractal analysis adversarial robustness wavelet packet decomposition market efficiency |
| title | Multifractal Carbon Market Price Forecasting with Memory-Guided Adversarial Network |
| title_full | Multifractal Carbon Market Price Forecasting with Memory-Guided Adversarial Network |
| title_fullStr | Multifractal Carbon Market Price Forecasting with Memory-Guided Adversarial Network |
| title_full_unstemmed | Multifractal Carbon Market Price Forecasting with Memory-Guided Adversarial Network |
| title_short | Multifractal Carbon Market Price Forecasting with Memory-Guided Adversarial Network |
| title_sort | multifractal carbon market price forecasting with memory guided adversarial network |
| topic | carbon market price prediction multifractal analysis adversarial robustness wavelet packet decomposition market efficiency |
| url | https://www.mdpi.com/2504-3110/9/7/403 |
| work_keys_str_mv | AT nali multifractalcarbonmarketpriceforecastingwithmemoryguidedadversarialnetwork AT mingzhutang multifractalcarbonmarketpriceforecastingwithmemoryguidedadversarialnetwork AT jingwendeng multifractalcarbonmarketpriceforecastingwithmemoryguidedadversarialnetwork AT liranwei multifractalcarbonmarketpriceforecastingwithmemoryguidedadversarialnetwork AT xinpengzhou multifractalcarbonmarketpriceforecastingwithmemoryguidedadversarialnetwork |