The accurate and stable prediction of crude oil prices holds significant value, providing insightful guidance for investors and decision-makers. The intricate interplay of factors influencing oil prices and the pronounced fluctuations present significant obstacles within the realm of oil price forecasting. This study introduces a novel hybrid model framework, distinct from the conventional methods, that integrates influencing factors for oil price prediction. First, using Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) extract mode components from crude oil prices. Second, using the Adaptive Copula-based Feature Selection (ACBFS), rooted in Copula theory, facilitates the integration of the influencing factors; ACBFS enhances both accuracy and stability in feature selection, thereby amplifying predictive performance and interpretability. Third, low-frequency modes are predicted through an Attention Mechanism-based Long and Short-Term Memory Neural Network (AM-LSTM), optimized using Bayesian Optimization and Hyperband (BOHB). Conversely, high-frequency modes are forecasted using Extreme Gradient Boosting Models (XGboost). Finally, the error correction mechanism further enhances the predictive accuracy. The experimental results show that the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of the proposed hybrid prediction framework are the lowest compared to the benchmark model, at 0.7333 and 1.1069, respectively, which proves that the designed prediction structure has better efficiency and higher accuracy and stability.

Accurate carbon price forecasts are crucial for policymakers and enterprises to understand the dynamics of carbon price fluctuations, enabling them to formulate informed policies and investment strategies. However, due to the non-linear and non-stationary nature of carbon price, traditional models often struggle to achieve high prediction accuracy. To address this challenge, this study proposes a novel integrated prediction framework designed to enhance forecast accuracy. First, the carbon price series is decomposed into a series of smoother subsequences using fast iterative filtering (FIF). Subsequently, an integrated prediction model, AM-TCN-LSTM, is constructed, incorporating the attention mechanism (AM), temporal convolutional networks (TCN), and long short-term memory (LSTM) neural networks. The attention mechanism adaptively captures complex features from multiple factors, while the TCN-LSTM efficiently extracts temporal features from the sequences. Finally, the results from each subsequence are aggregated to generate the final prediction. Five carbon markets in china: Guangdong, Hubei, Shenzhen, Beijing, and Shanghai were selected to verify the validity of the proposed model. Various comparative models and evaluation metrics were employed to assess performance. The results demonstrate that: (1) the TCN-LSTM model achieves higher prediction accuracy compared to single models. (2) FIF is a more effective decomposition method with superior performance compared to EMD-based methods. (3) The proposed model exhibits the highest predictive capability, with MAE values of 0.0964, 0.1403, 1.9476, 2.0848, and 0.5029 for the five carbon markets, significantly outperforming comparison models. (4) The attention mechanism effectively captures the influence of multiple factors on carbon price, particularly within the short-term components.

In today’s environmentally conscious world, carbon trading has emerged as a widely accepted economic instrument to mitigate the externalities resulting from deteriorating environmental problems. Consequently, the use of market-based mechanisms to address environmental issues has reached a global consensus. Many countries are implementing progressive steps by establishing carbon markets to promote low-carbon development and meet their carbon reduction targets. However, the inherent risks in carbon trading markets may hamper the formation of a reasonable carbon price signal, leading to inadequate stimulation of low-carbon technology investments and potential failure to achieve national emission reduction goals. Therefore, managing the risks associated with carbon trading markets is crucial. This study focuses on measuring the risk of China’s carbon market, with the primary aim of exploring carbon price fluctuation patterns and precisely measuring market risks. The risks associated with China’s carbon market are quantified and analyzed using the exponential generalized autoregressive conditional heteroskedasticity (EGARCH) model, extreme value theory (EVT), and the value at risk (VaR) method. Results show that (1) the effect of external shocks on each carbon market is asymmetrical, and positive shocks exert considerable leverage effects on carbon price fluctuations. (2) EVT can be used to effectively fit the risks in the carbon markets. The risks of each carbon market show different characteristics. The risk of Hubei and Guangdong carbon markets is relatively small, and the dynamic VaR is nearly ±0.2. (3) Compared with the performance of the Chinese carbon market, the performance of the European Union Emission Trading Scheme is more stable, and its dynamic VaR for most of the period is within ±0.1, which is considerably lower than the VaR of other Chinese carbon markets. This study also proposes suitable policy implications to ensure the healthy and sustainable development of China’s carbon market.

The rapid development of the digital economy (DE) provides a new driving force for high-quality tourism development (HQTD). How to coordinate HQTD and DE is an urgent issue to be resolved. In this study, the coupling coordination degree (CCD) between HQTD and DE in Chinese prefecture-level cities is analysed using the CCD model, and the factors driving CCD are identified by Shapley additive explanations (SHAP). The results show that (1) Chinese city-level HQTD and DE show a rising trend from 2010 to 2019. The national average rises from 0.1807 and 0.2434 in 2010 to 0.2318 and 0.4113 in 2019, respectively, with HQTD’s development lagging noticeably behind DE. (2) CCD exhibits marked inter-regional disparities and intra-regional clustering. The northwest region has the lowest values, with many cities’ CCD below 0.5, indicating an imbalanced status. In 2019, all cities in the eastern region are in a balanced status, with Shanghai exceeding 0.8. (3) Total social retail sales per capita and percentage of tertiary sector are the key drivers of CCD; economic development and urbanisation rate exhibit a non-linear relationship with CCD. The CCD in developed cities in the east and north is driven by consumption, whereas the northwest region is primarily influenced by factors related to labour capital. Based on these conclusions, some policy implications are provided for the synergistic development of HQTD and DE.