A hybrid model for carbon price forecasting using GARCH and long short-term memory network

Abstract The reform of the EU ETS markets in 2017 has induced new carbon price forecasting challenges. This study proposes a novel decomposition-ensemble paradigm VMD-GARCH/LSTM-LSTM model to better adapt to the current fast-rising and volatile carbon price. Three significant steps are involved: (1) the Variational Mode Decomposition (VMD) algorithm decomposes the carbon price series into sub-modes; (2) The Long Short-Term Memory (LSTM) network predicts low-frequency sub-modes, with the GARCH model predicting high-frequency sub-modes; (3) the forecasts from sub-modes are ensembled through the LSTM non-linear ensemble method. Combining econometric and artificial intelligence methods, our proposed model has an excellent performance on the current carbon price, with smaller errors than single econometrics or AI models or decomposition-ensemble models with linear simple superposition approaches. VMD have significant advantages over their alternative algorithms. Moreover, the LSTM involved in our model is well suited to forecast the rising carbon price in late EU ETS Phase III, providing good insight into risk aversion for participants.

[1]  Peter Reinhard Hansen,et al.  The Model Confidence Set , 2010 .

[2]  Ling Tang,et al.  A decomposition–ensemble model with data-characteristic-driven reconstruction for crude oil price forecasting , 2015 .

[3]  Wei Li,et al.  The research on setting a unified interval of carbon price benchmark in the national carbon trading market of China , 2015 .

[4]  T. Bollerslev,et al.  Generalized autoregressive conditional heteroskedasticity , 1986 .

[5]  Jörn C. Richstein,et al.  The market (in-)stability reserve for EU carbon emission trading: Why it might fail and how to improve it , 2015 .

[6]  Qunwei Wang,et al.  Dynamic Correlation and Risk Contagion Between “Black” Futures in China: A Multi-scale Variational Mode Decomposition Approach , 2018, Computational Economics.

[7]  Chengshi Tian,et al.  A hybrid framework for carbon trading price forecasting: The role of multiple influence factor , 2020 .

[8]  Uta Pigorsch,et al.  Nonlinearity in Cap-and-Trade Systems: The EUA Price and its Fundamentals , 2013 .

[9]  Jianping Li,et al.  A novel hybrid ensemble learning paradigm for nuclear energy consumption forecasting , 2012 .

[10]  Qunwei Wang,et al.  Flying into the future: A scenario-based analysis of carbon emissions from China's civil aviation , 2020, Journal of Air Transport Management.

[11]  Qunwei Wang,et al.  Multi-scale dependence structure and risk contagion between oil, gold, and US exchange rate: A wavelet-based vine-copula approach , 2020 .

[12]  F. Diebold,et al.  Comparing Predictive Accuracy , 1994, Business Cycles.

[13]  Stefan Trück,et al.  Modeling the Price Dynamics of Co2 Emission Allowances , 2009 .

[14]  Feng Ma,et al.  Forecasting realized volatility in a changing world: A dynamic model averaging approach , 2016 .

[15]  Yonghui Sun,et al.  A Carbon Price Forecasting Model Based on Variational Mode Decomposition and Spiking Neural Networks , 2016 .

[16]  Duc Khuong Nguyen,et al.  Nonlinearities in carbon spot-futures price relationships during Phase II of the EU ETS , 2012 .

[17]  Qunwei Wang,et al.  Drivers of civil aviation carbon emission change: A two-stage efficiency-oriented decomposition approach , 2020 .

[18]  Peter Bloomfield,et al.  Fourier Analysis of Time Series: An Introduction , 1977 .

[19]  Heiða Njóla Guðbrandsdóttir.  Predicting the Price of EU ETS Carbon Credits: A Correlation, Principal Component and Latent Root Approach , 2011 .

[20]  Ling Tang,et al.  A novel mode-characteristic-based decomposition ensemble model for nuclear energy consumption forecasting , 2015, Ann. Oper. Res..

[21]  Carolina García-Martos,et al.  Modelling and forecasting fossil fuels, CO2 and electricity prices and their volatilities , 2013 .

[22]  Tao Zhang,et al.  Forecasting carbon price using empirical mode decomposition and evolutionary least squares support vector regression , 2017 .

[23]  Qunwei Wang,et al.  How does emission trading reduce China's carbon intensity? An exploration using a decomposition and difference-in-differences approach. , 2019, The Science of the total environment.

[24]  Julien Chevallier,et al.  Price drivers and structural breaks in European carbon prices 2005–2007 , 2008 .

[25]  K. Sommerfeld,et al.  Why does emissions trading under the EU Emissions Trading System (ETS) not affect firms’ competitiveness? Empirical findings from the literature , 2018, Climate Policy.

[26]  Bangzhu Zhu.  A Novel Multiscale Ensemble Carbon Price Prediction Model Integrating Empirical Mode Decomposition, Genetic Algorithm and Artificial Neural Network , 2012 .

[27]  Grischa Perino,et al.  Procrastinating reform: The impact of the market stability reserve on the EU ETS , 2016 .

[28]  Yi-Ming Wei,et al.  Carbon price forecasting with a novel hybrid ARIMA and least squares support vector machines methodology , 2013 .

[29]  Ulrik Beck,et al.  Endogenizing the Cap in a Cap-and-Trade System: Assessing the Agreement on EU ETS Phase 4 , 2020, Environmental and Resource Economics.

[30]  Julien Chevallier,et al.  On the realized volatility of the ECX CO2 emissions 2008 futures contract: distribution, dynamics and forecasting , 2009 .

[31]  Yi-Ming Wei,et al.  Carbon price volatility: Evidence from EU ETS , 2011 .

[32]  George S. Atsalakis,et al.  Using computational intelligence to forecast carbon prices , 2016, Appl. Soft Comput..

[33]  Minggang Wang,et al.  Carbon price forecasting with complex network and extreme learning machine , 2020 .

[34]  Mohammadamin Azimi,et al.  Carbon trading volume and price forecasting in China using multiple machine learning models , 2020 .

[35]  Li Yang,et al.  Forecasting crude oil market volatility: A Markov switching multifractal volatility approach , 2016 .

[36]  Abraham Lempel,et al.  On the Complexity of Finite Sequences , 1976, IEEE Trans. Inf. Theory.

[37]  Grischa Perino,et al.  EU-ETS Phase IV: allowance prices, design choices and the market stability reserve , 2017 .

[38]  Lili Ding,et al.  Usefulness of economic and energy data at different frequencies for carbon price forecasting in the EU ETS , 2018 .

[39]  Qunwei Wang,et al.  Effect of China's western development strategy on carbon intensity , 2019, Journal of Cleaner Production.

[40]  Julien Chevallier,et al.  Nonparametric modeling of carbon prices , 2011 .

[41]  Gary Koop,et al.  Forecasting the European carbon market , 2013 .

[42]  Yan Hao,et al.  Point and interval forecasting for carbon price based on an improved analysis-forecast system , 2020, Applied Mathematical Modelling.

[43]  Jia-Qi Zhu,et al.  Improved EEMD-based crude oil price forecasting using LSTM networks , 2019, Physica A: Statistical Mechanics and its Applications.

[44]  Qunwei Wang,et al.  Does emission trading lead to carbon leakage in China? Direction and channel identifications , 2020 .

[45]  Julien Chevallier,et al.  Volatility forecasting of carbon prices using factor models , 2010 .

[46]  Dominique Zosso,et al.  Variational Mode Decomposition , 2014, IEEE Transactions on Signal Processing.

[47]  Ling Tang,et al.  A novel decomposition ensemble model with extended extreme learning machine for crude oil price forecasting , 2016, Eng. Appl. Artif. Intell..

[48]  Paolo Piselli,et al.  Effects of European emission unit allowance auctions on corporate profitability , 2020 .

[49]  Tao Zhang,et al.  A novel multiscale nonlinear ensemble leaning paradigm for carbon price forecasting , 2018 .

[50]  Raphael N. Markellos,et al.  Modeling CO2 Emission Allowance Prices and Derivatives: Evidence from the European Trading Scheme , 2008 .

[51]  Zhongfu Tan,et al.  A hybrid model using signal processing technology, econometric models and neural network for carbon spot price forecasting , 2018, Journal of Cleaner Production.

[52]  Sonnan Chen,et al.  Pricing derivatives with modeling CO2 emission allowance using a regime-switching jump diffusion model: with regime-switching risk premium , 2016 .

[53]  Wei Sun,et al.  Analysis and forecasting of the carbon price using multi—resolution singular value decomposition and extreme learning machine optimized by adaptive whale optimization algorithm , 2018, Applied Energy.

[54]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[55]  Lixin Tian,et al.  Chaotic characteristic identification for carbon price and an multi-layer perceptron network prediction model , 2015, Expert Syst. Appl..

[56]  Qunwei Wang,et al.  Scenario-based potential effects of carbon trading in China: An integrated approach , 2016 .

[57]  S. Byun,et al.  Forecasting carbon futures volatility using GARCH models with energy volatilities , 2013 .

[58]  Yi-Ming Wei,et al.  An Adaptive Multiscale Ensemble Learning Paradigm for Nonstationary and Nonlinear Energy Price Time Series Forecasting , 2016 .

[59]  Marc S. Paolella,et al.  An econometric analysis of emission allowance prices , 2008 .

[60]  Julien Chevallier,et al.  A model of carbon price interactions with macroeconomic and energy dynamics , 2011 .

[61]  Kaijian He,et al.  A multiscale analysis for carbon price drivers , 2019, Energy Economics.