Energy futures prices forecasting by novel DPFWR neural network and DS-CID evaluation

Forecasting carbon emissions future prices using the machine learning methods

Due to the uncertainty surrounding the coupling and decoupling of natural gas, oil, and energy commodity futures prices, the current study seeks to investigate the interactions between energy commodity futures, oil price futures, and carbon emission futures from a forecasting perspective with implications for environmental sustainability. We employed daily data on natural gas futures prices, crude oil futures prices, carbon futures prices, and Dow Jones energy commodity futures prices from January 2018 to October 2021. For empirical analysis, we applied machine learning tools including traditional multiple linear regression (MLR), artificial neural network (ANN), support vector regression (SVR), and long short-term memory (LSTM). The machine learning analysis provides two key findings. First, the nonlinear frameworks outperform linear models in developing the relationships between future oil prices (crude oil and heating oil) and carbon emission futures prices. Second, the machine learning findings establish that when oil prices and natural gas prices display extreme movement, carbon emission futures prices react nonlinearly. Understanding the nonlinear dynamics of extreme movements can help policymakers design climate and environmental policies, as well as adjust natural gas and oil futures prices. We discuss important implications to sustainable development goals mainly SDG 7 and SDG 12.

Forecasting Crude Oil Prices with a WT-FNN Model

In order to improve the accuracy of forecasting crude oil prices, a new crude oil price forecasting method is introduced in the paper that is a combination of the FNN model and the stochastic time effective function—namely, the WT-FNN model. The FNN model keeps track of the historical values of crude oil prices and predicts future crude oil prices, and the stochastic time effective function gives greater weight to recent information and smaller weight to old information, thus making the prediction of crude oil prices more reasonable. We selected the daily data of Brent crude oil prices from 4 January 2000 to 30 September 2021 as research objects and then used the WT-FNN model to train and predict the research objects. By comparing it to the benchmark model, we found that the predictive effect of the WT-FNN model was better than the FNN model and the no-change model. The results also passed a robustness test.