现有研究
交易市场的可预测性
Efficient Market Hypothesis，Emerging Market Intelligence Hypothesis
Decomposition-integration
分解原有时间序列数据为多个部分，分别预测，再整合为最终结果
相关文献:
- Ensemble wind speed forecasting with multi-objective Archimedes optimization algorithm and sub-model selection（风速预测，2021.11）
- Efficient bootstrap stacking ensemble learning model applied to wind power generation forecasting（风能预测，2022.3）
- A hybrid model for multi-step coal price forecasting using decomposition technique and deep learning algorithms（煤碳价预测，2022.1）
- Electricity Price Forecasting Based on Self-Adaptive Decomposition and Heterogeneous Ensemble Learning（电价预测，2020.10）
- A novel machine learning-based electricity price forecasting model based on optimal model selection strategy（电价预测，2022.1）
- Novel hybrid model based on echo state neural network applied to the prediction of stock price return volatility（股价预测，2021.12）
- Forecasting the movements of Bitcoin prices: an application of machine learning algorithms（比特币价格预测，2020.11）
- A Novel Multiscale Ensemble Carbon Price Prediction Model Integrating Empirical Mode Decomposition, Genetic Algorithm and Artificial Neural Network（碳价预测，2012.2）
Improve
- Sample Entropy integration
An innovative random forest-based nonlinear ensemble paradigm of improved feature extraction and deep learning for carbon price forecasting（碳价预测，2021.3） - Secondary decomposition
A new secondary decomposition ensemble learning approach for carbon price forecasting（碳价预测，2021.2） - Clustering
Carbon Price Analysis Using Empirical Mode Decomposition（碳价预测，2013.12） - signal decomposition (CEEMDAN)
Carbon price forecasting based on CEEMDAN and LSTM（碳价预测，2022.4）
ETS运作机制
碳排放许可分配机制
碳排放标准计量体系
碳测算
价格机制
碳价预测
- 结合CEEMDAN与LSTM（2022）
- 基于广州碳市场
- CEEMDAN（Complete Ensemble Empirical Mode Decomposition with Adaptive Noise）使用Sample Entropy和Variational Modal Decomposition（VMD）进一步提高了预测的准确性