Forecasting European carbon returns using dimension reduction techniques: Commodity versus financial fundamentals

Tan, Xueping; Sirichand, Kavita; Vivian, Andrew; Wang, Xinyu

doi:10.1016/j.ijforecast.2021.07.005

Cited by 22 publications

(11 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the 13 financial indicators and 25 commodity indicators are selected from previous typical literature where these indicators show considerable predictive power in carbon price forecasting. The 13 financial indicators include secondary market interest rates for 3-month Treasury bill, 10-year national bond rate [ 9 ], S&P 500 index, Dow Jones Composite Index, Shanghai Composite Index, Shenzhen Composite Index, 5-Year Bond Index Yield, WilderHill New Energy Global Innovation Index (NEX), WilderHill Clean Energy Index (CEI) [ 10 ], AAA-rated corporate bond spreads, daily spread of 1-year Treasury bill and 10-year government bond [ 11 ], USD/CNY and China’s Economic Policy Uncertainty Index [ 12 ].…”

Section: Methodsmentioning

confidence: 99%

“…The 25 commodity indicators include ICE-UK natural gas continuous futures price (UKGP), Asia gas price (JKM), S&P GSCI Gas oil index excess return (GGO) [ 10 ], ICE-coal Rotterdam continuous futures price (GP), ICE-Brent crude oil continuous futures price (BOP) [ 13 ], S&P GSCI Crude oil index excess return (GCO), EUA price, China Electricity Price index and 17 S&P GSCI non-energy commodity indexes (GGOL, GSIL, GALU, GCOP, GLEA, GNIC, GZIN, GCOC, Gcof, Gcor, GCOT, Gsoy, Gsug, Gwhe, GFC, GLH, GLC) [ 14 ].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Carbon price prediction based on a scaled PCA approach

Wei,

Ouyang

2024

PLoS ONE

View full text Add to dashboard Cite

Carbon price prediction is of great importance to regulators and participants in the carbon trading market. It is the basis for developing policies related to the carbon trading market and stabilizing that market. Considering the numerous factors that influence carbon prices in China, dimensionality reduction is needed to improve the prediction accuracy and efficiency. However, the traditional dimensionality reduction methods fail to fully consider the role of influencing factors, which has certain limitations. In this paper, a new dimensionality reduction method, namely scaled principal component analysis (s-PCA), is employed to improve the prediction accuracy of carbon prices. Firstly, a factor library that influence carbon prices is constructed from three perspectives: technical indicators, financial indicators and commodities indicators. Then, the s-PCA method is used to reduce the dimensionality of factors influencing carbon price. Next, two different methods are used to predict carbon prices, including traditional regression method and Long Short-Term Memory (LSTM) method. Finally, the economic value of the s-PCA method is examined by constructing investment portfolios. The empirical results of the Hubei Emissions Exchange show that the s-PCA model outperforms other competing models both in- and out-of-sample. In addition, the LSTM model could improve the performance of the s-PCA model in carbon price prediction. From a market timing perspective, investors can achieve a greater return and a larger Sharpe ratio using the s-PCA method than using other comparative methods and buy-and-hold strategy. Therefore, the s-PCA method is effective and robust in predicting carbon price.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Carbon price prediction based on a scaled PCA approach

Wei,

Ouyang

2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Third, weekly prices/returns capture dynamic prices better than daily and monthly data, thus considering that daily data may induce potential biases arising from bid–ask effects, nonsynchronous trading days and the effects of illiquidity on asset prices. Meanwhile, monthly data may be subject to effects derived from time aggregation and compensation effects (Kang et al, 2017; Tan et al, 2022). Thus, our sample comprises 582 weekly observations.…”

Section: Methodsmentioning

confidence: 99%

“…">Data collection Carbon and oil prices are proxied by the Intercontinental Exchange‐Carbon Emission Allowances (ICE‐EUA) Phase 3 Futures contract and West Texas Intermediate (WTI) prices, respectively, downloaded from the Bloomberg platform for the period between 7/12/2012 and 01/26/2024. As proposed by Zhao et al (2018), Xu et al (2020) and Tan et al (2022), we employ weekly data considering the following reasons. First, the main traders in the carbon markets are focused on long horizon carbon price changes because it enables them to optimise their trading strategies.…”

Section: Methodsmentioning

confidence: 99%

Predicting carbon and oil price returns using hybrid models based on machine and deep learning

Molina‐Muñoz,

Mora‐Valencia,

Perote

2024

Intell Sys Acc Fin Mgmt

View full text Add to dashboard Cite

SummaryPredicting carbon and oil prices is recently gaining relevance in the climate change literature. This is due to the fact that conventional energy market analysis and the design of mechanisms for climate change mitigation constitute key variables for artificial carbon markets. Yet, modelling non‐linear effects in time series remains a major challenge for carbon and oil price forecasting. Hence, hybrid models seem to be appealing alternatives for this purpose. This study evaluates the performance of 12 hybrid models, which weigh results from random forest, support vector machine, autoregressive integrated moving average and the non‐linear autoregressive neural network models. The weights are determined by (i) assuming equal weights, (ii) using a neural network to optimise individual weights and (iii) employing deep learning techniques. The findings of our work confirm the salient characteristics of modelling the non‐linear effects of time series and the potential of hybrid models based on neural networks and deep learning in predicting carbon and oil price returns. Furthermore, the best results are obtained from hybrid models that combine machine learning and traditional econometric techniques as inputs, which capture the linear and non‐linear effects of time series.

show abstract

“…. In addition, the 13 financial indicators and 25 commodity indicators are chosen from previous literature, which shows considerable predictive power in carbon price forecasting [30][31][32][33][34][35]. The details of the financial indicators and commodity indicators are described in Tables 2 and 3, respectively.…”

Section: Methodsmentioning

confidence: 99%

Forecasting Carbon Price Using Double Shrinkage Methods

Wei

Ouyang

2023

IJERPH

View full text Add to dashboard Cite

It is commonly recognized that setting a reasonable carbon price can promote the healthy development of a carbon trading market, so it is especially important to improve the accuracy of carbon price forecasting. In this paper, we propose and evaluate a hybrid carbon price prediction model based on so-called double shrinkage methods, which combines factor screening, dimensionality reduction, and model prediction. In order to verify the effectiveness and superiority of the proposed model, this paper takes data from the Guangdong carbon trading market for empirical analysis. The sample interval is from 5 August 2013 to 25 March 2022. Based on the results of the empirical analysis, several main findings can be summarized. First, the double shrinkage methods proposed in this paper yield more accurate prediction results than various alternative models based on the direct application of factor screening methods or dimensionality reduction methods, when comparing R2, root-mean-square error (RMSE), and root absolute error (RAE). Second, LSTM-based double shrinkage methods have superior prediction performance compared to LR-based double shrinkage methods. Third, these findings are robust with the use of normalized data, different data frequencies, different carbon trading markets, and different dataset divisions. This study provides new ideas for carbon price prediction, which might have a theoretical and practical contributions to complex and non-linear time series analysis.

show abstract

Forecasting European carbon returns using dimension reduction techniques: Commodity versus financial fundamentals

Cited by 22 publications

References 87 publications

Carbon price prediction based on a scaled PCA approach

Carbon price prediction based on a scaled PCA approach

Predicting carbon and oil price returns using hybrid models based on machine and deep learning

Forecasting Carbon Price Using Double Shrinkage Methods

Contact Info

Product

Resources

About