WTI Crude Oil Futures Research Articles

Hybrid Prediction Model for International Crude Oil Prices Based on EEMD and SE Reconstruction Methods

Accurate prediction of crude oil prices can provide references for the energy economy and valuable guidance for investors and decision-makers in formulating strategies. However, due to the complexity and volatility of the crude oil market, achieving accurate and reliable crude oil price forecasts is challenging. Therefore, this paper proposes a hybrid forecasting model for crude oil prices that combines Ensemble Empirical Mode Decomposition (EEMD) and Sample Entropy (SE) reconstruction. Firstly, the daily closing price data of WTI crude oil futures from January 2, 2018, to March 21, 2024, is selected. The EEMD method is used to decompose the original data, and the decomposed sub-sequences are reconstructed and merged into high-frequency, mid-frequency, and low-frequency sequences using Sample Entropy (SE). Finally, these sequences are input into six machine learning models for prediction and comparison. The research results show that, firstly, by comparing the R2, RMSE, MAE, and MAPE values, it can be seen that the forecasting ability of the EEMD-SE hybrid forecasting model is significantly better than the EEMD hybrid forecasting model, indicating that the combination of SE methods can effectively improve the model s forecasting ability. Secondly, the EEMD-SE-LSTM model has higher prediction accuracy than other models. Finally, the comparison of models reveals that the BP neural network exhibits the greatest improvement after SE reconstruction. Therefore, it is recommended to improve the crude oil futures price forecasting and risk warning system.

Do OPEC+ policies help predict the oil price: A novel news-based predictor

The OPEC+, composed of the Organization of the Petroleum Exporting Countries (OPEC) and non-OPEC oil-producing countries, exerts considerable influence over the global crude oil market. However, existing literature lacks a comprehensive application of this factor in oil price forecasting, primarily due to the complexity of measuring such policy evolutions. To address this research gap, this study develops a news-based OPEC+ policy index based on text mining methods for comprehensive analysis and forecasting of the oil price. First, by crawling and mining news headlines related to OPEC+ production decisions, a dynamic and high-frequency (weekly) OPEC+ policy index is established. Second, the linear and nonlinear relationship between the proposed OPEC+ policy index and the WTI crude oil futures price is thoroughly examined, assessing the potential predictive power of the index in explaining the movements of the crude oil price. Third, the forecasting efficacy of the constructed index on the oil price is rigorously evaluated across eight econometric and machine learning models. Key findings include: (1) The proposed weekly OPEC+ policy index demonstrates strong concordance with OPEC+ production change decisions, exhibiting notable peaks and troughs corresponding to OPEC+ Ministerial Meetings. (2) The relationship analysis demonstrates a strong linear and nonlinear association between the proposed OPEC+ policy index and the crude oil price. (3) For oil price prediction, models incorporating our proposed OPEC+ policy index demonstrate superior performance compared to models without this index. In particular, the index exhibits a more significant predictive effect within three-week forecasting horizons and performs exceptionally well during periods of pandemic and the Russia-Ukraine conflict. In addition, the OPEC+ policy index also exhibits a significant predictive effect on the daily crude oil price and natural gas price, further confirming the robust and powerful forecasting capability of this index within the energy system.

Volatility spillover between oil prices and main exchange rates: Evidence from a DCC-GARCH-connectedness approach

This paper investigates the co-movements of oil prices and the exchange rates of 10 top oil-importing and oil-exporting countries. First, we estimated the total static spillover index based on vector autoregressive (VAR) models. Second, we adopted the recent DCC-GARCH-CONNECTEDNESS approach proposed by Gabauer (2020) to conduct a time-varying analysis that investigates the directionally dynamic connectedness among WTI and Shanghai crude oil futures and currency markets. We explored contagion spillover volatility by focusing on a sample of major oil-exporting and oil-importing countries using daily data from 4 March 2018 to 25 August 2023. We analysed this relationship during four phases: the entire sample; before COVID-19; during COVID-19; and during the Russian‒Ukrainian war. Our results confirm the persistence of volatility for the series studied, thereby justifying the use of the dynamic connectedness approach. Our findings also reveal strong evidence of volatility transmission between oil prices and exchange-rate markets. However, the COVID-19 pandemic and the Russian‒Ukrainian war have altered this link. The connectedness between the two markets (petrol and exchange) was stronger at the beginning of the crisis period and then gradually depreciated in value over time. Our findings reveal that exchange rates for both oil-exporting and oil-importing countries are more sensitive to oil price shocks during crises than in normal periods. This suggests that volatility contagion between these two markets continues to exist, thus emphasising the role of oil price shocks as net transmitters across the network during extreme scenarios.

Exploring the Dynamics of CPO Spot and Futures Prices in Relation to Global Crude Oil Price: Evidence from India using ARDL Model Approach and Granger Causality Tests

This study examines the connection between Crude Palm Oil (CPO) spot and futures prices, and global crude oil prices using ARDL model and Granger causality tests to analyze data collected between January 2011 and April 2022, including CPO spot and futures prices, MCX, and WTI Crude oil futures. The results from the coefficient estimations show that both CPO future price percentage changes and crude oil price have a statistically significant impact on the CPO spot price. The study also reveals a long-term relationship between the dependent and independent variables in the level’s comparison. The study also demonstrates that global crude oil prices can significantly influence the spot and futures prices of CPO. This research provides useful insight for stakeholders in the palm oil industry, policymakers, and investors.

Carbon Futures Volatility Forecasting: The Role of Spillover Effect from Crude Oil Futures Market

Accurate prediction of the volatility of EU carbon emission quota futures is an important foundation for pricing derivative products, portfolio allocation, and risk management. On the basis of the GARCH-MIDAS model involving mixed frequency data sampling, this article considers the spillover effect of Brent crude oil futures market on carbon quota futures market, and incorporates the spillover effect into the prediction of carbon quota futures volatility to construct the VS-GARCH-MIDAS model. Using the monthly realized volatility of Brent crude oil futures as a proxy variable to reflect spillover effects, empirical results indicate the existence of a one-way spillover effect of Brent crude oil futures market on carbon quota futures market. Moreover, the GARCH-MIDAS model considering spillover effects has better in sample fitting performance and stronger out of sample predictive ability than the original GARCH-MIDAS model. To ensure the robustness of this conclusion, this paper also investigates the impact of spillover effects generated by WTI crude oil futures on the volatility of EUA futures, and concludes that the GARCH-MIDAS model considering spillover effects can improve the prediction accuracy of EUA futures volatility.

The Impact of the Fed's Interest Rate Adjustment Cycle on the Price of WTI Crude Oil Futures

This article is based on monthly data from January 2016 to January 2022, including the US Federal Funds Rate and WTI crude oil futures price index. A TVP-VAR model is constructed to study the impact of the Federal Reserve's interest rate cycles on WTI crude oil futures prices. The research found a positive correlation between crude oil futures prices and the Federal Reserve's interest rate cycles. That means that when the Federal Reserve raises or lowers the US Federal Funds Rate, it leads to an increase or decrease in crude oil futures prices. Therefore, it is believed that in the current context of global quantitative easing and the sustained rise in international crude oil prices, China should formulate a new energy strategy that matches the high-quality development of the social economy and accelerate the transformation and upgrading of the crude oil industry.

Spillover relationship between different oil shocks and high- and low-carbon assets: An analysis based on time-frequency spillover effects

In this paper, the spillover relationship between different oil shocks and high- and low-carbon assets is investigated through DY and BK spillover methods. It is found that the spillover relationships between them are heterogeneous, with WTI crude oil futures and heating oil futures being highly affected by oil demand and supply shocks, and clean energy sector stocks being highly affected by oil risk shocks. The spillover relationship between them changes at different time frequencies. For high- and low-carbon assets, more attention should be paid to protecting against risks from the same assets. Natural gas futures are little affected by spillovers.

How does bubble risk propagate among financial assets? A perspective from the BSADF-vine copula model

In this paper, the BSADF method is used to construct the bubble net value sequence of 11 mainstream financial assets, and the vine copula model is used to analyze the characteristics of the bubble-related structure. First, we use the BSADF method to measure the bubbles of various financial assets. The results show that since the outbreak of COVID-19, most types of assets have experienced a sharp bubble rise and their longest bubble period as central banks have implemented quantitative easing policies. Furthermore, this article reveals the path characteristics of bubble risk transmission in different assets using the vine copula model. The R vine copula is found to be best for analyzing the tail dependence structure. The S&P 500 and the international gold price occupy the hub position in the bubble dependence structure of various financial assets. The Shanghai Composite Index and the US Dollar Index can act as relays and accelerators in the transmission of bubble risk across the financial system. Finally, we explore the tail dependence structure between financial assets. The results indicate that gold can be a good hedge against the bubble risk of the Hang Seng Index and WTI crude oil futures. The COVID-19 pandemic and accommodative monetary policies by governments can create conditions for bubble risk to spread between assets such as Bitcoin and China’s 10-year Treasury bonds and between the US Dollar Index and the S&P 500.

Selective hedging strategies for crude oil futures based on market state expectations

This paper studies the ex-ante selective hedging strategies of crude oil futures contracts based on market state expectations and compares the hedging performances to the traditional minimum variance routine hedging strategies. The main advantage of the proposed method is that it achieves a trade-off between return and risk, rather than hedges risk at all costs. Specifically, we first use a multi-input Hidden Markov Model(HMM) to identify the market state, assess the market’s herding impact, and then integrate the findings of identification and measurement to forecast the price trend. We offer an adjustment criterion for the hedge ratios driven by GARCH22GARCH is the abbreviation of Generalized AutoRegressive Conditional Heteroskedasticity.-type models based on the anticipated market state. We conducted an empirical analysis to examine the hedging effect of WTI and Brent crude oil futures, the results indicate that the proposed state-dependent hedging strategies are superior to the traditional model-driven hedging strategies concerning the hedged portfolio based on four criteria. The robustness check reveals that the proposed hedging strategies still outperform in different market situation. The findings can help traders in the crude oil markets, and the methodology can be applied to other energy markets.

Integrating Economic Theory, Domain Knowledge, and Social Knowledge into Hybrid Sentiment Models for Predicting Crude Oil Markets

For several decades, sentiment analysis has been considered a key indicator for assessing market mood and predicting future price changes. Accurately predicting commodity markets requires an understanding of fundamental market dynamics such as the interplay between supply and demand, which are not considered in standard affective models. This paper introduces two domain-specific affective models, CrudeBERT and CrudeBERT+, that adapt sentiment analysis to the crude oil market by incorporating economic theory with common knowledge of the mentioned entities and social knowledge extracted from Google Trends. To evaluate the predictive capabilities of these models, comprehensive experiments were conducted using dynamic time warping to identify the model that best approximates WTI crude oil futures price movements. The evaluation included news headlines and crude oil prices between January 2012 and April 2021. The results show that CrudeBERT+ outperformed RavenPack, BERT, FinBERT, and early CrudeBERT models during the 9-year evaluation period and within most of the individual years that were analyzed. The success of the introduced domain-specific affective models demonstrates the potential of integrating economic theory with sentiment analysis and external knowledge sources to improve the predictive power of financial sentiment analysis models. The experiments also confirm that CrudeBERT+ has the potential to provide valuable insights for decision-making in the crude oil market.

Dependence and spillover among oil market, China's stock market and exchange rate: new evidence from the Vine-Copula-CoVaR and VAR-BEKK-GARCH frameworks

We first employ the method of multivariate GARCH models and Vine-Copula-CoVaR to analyse relationships between dependence, systematic risk spillover, and volatility spillover between the USD/CNY exchange rate and the returns on WTI crude oil futures and the Chinese stock market since China's 2005 foreign exchange reform. We utilise daily data from 2005 to 2020. We find a more complex dependence of the USD/CNY exchange rate on stock markets and WTI crude oil prices. All have negative risk spillovers among paired markets, with WTI having the most substantial risk spillover. However, the strength of the systematic risk spillover varies across markets. Based on the results of the VAR(1)-BEKK-GARCH (1,1) and Wald tests confirm that there is a substantial mean spillover from the Chinese stock market and the USD/CNY exchange rate to the WTI crude oil price, whereas there is a more significant spillover from the WTI crude oil price to Chinese stock market volatility. The empirical findings extend the systematic understanding of the international crude oil price shocks to the dependence and transmission mechanism between the Chinese stock market and the USD/CNY exchange rate (USD/CNY). Our findings can help investors and policymakers to manage risk better and develop more sensible market rules.

Multiscale online-horizontal-visibility-graph correlation analysis of financial market

In this study, we introduce an analogous multiscale online-horizontal-visibility-graph correlation analysis (MOHVGCA) method to quantify the association strength between pairwise nonlinear time series. The new method is based on complex network approaches and proved to be a powerful and efficient tool for large-scale time series analysis. The versatility and robustness of this new method are illustrated through synthetic series. Results obtained allow us to be optimistic about its efficiency in correlation analysis of complex time series. Furthermore, we employ the new method to characterize the association between WTI Crude Oil futures and representative traded currencies on 5 min intra-day recordings in the period January 2013–December 2015. The results reveal that there exist positive associations between WTI Crude Oil and the considered traded currencies, and the association degree between WTI Crude Oil and currencies from oil-exporting and oil-importing countries is significantly different over different scales. The oil crisis weakens the association between oil and the currencies from the oil-importing currencies and the information exchange between oil and currencies from oil-exporting countries strengthened dramatically after the oil crisis. Even more, we detect that the Russian ruble always has the strongest ties with oil in different periods. These findings shed new light on the correlation analysis from the perspective of multiscale network analysis.

Jumps in commodity prices: New approaches for pricing plain vanilla options

We present a new term-structure model for commodity futures prices based on Trolle and Schwartz (2009), which we extend by incorporating multiple jump processes. Our work explores the valuation of plain vanilla options on futures prices when the spot price follows a log-normal process, the forward cost of carry curve and the volatility are stochastic variables, and the spot price and the forward cost of carry allow for time-dampening jumps. We obtain an analytical representation of the characteristic function of the futures prices and, hence, also for plain vanilla option prices using the fast Fourier transform methodology. We price options on WTI crude oil futures contracts using our model and extant models. We obtain higher accuracy than earlier models and save significantly in computing time.

The relative pricing of WTI and Brent crude oil futures: Expectations or risk premia?

This paper studies the spread of Brent-WTI futures prices using a no-arbitrage term structure model with one common and two latent idiosyncratic risk factors. We document more negative risk premia for WTI than for Brent, and the differences are more pronounced at longer maturities. The expectation of future spot price dominates the risk premium in determining the term structure of Brent-WTI futures spread, especially at short maturities. The common risk premia in both markets are negative and similar, while their corresponding idiosyncratic risk premia have opposite signs. The common risk prices of WTI and Brent are generally related to the US crude commercial stock, inflation, economic uncertainty, and hedging pressure; however, idiosyncratic risk prices are more related to their corresponding local production, short rate, and the term structure factors. The variance decomposition indicates that the idiosyncratic factors account for a considerable part at longer forecast horizons in both markets.

The Linkage between Crude Oil and Stock market: Evidence from China and the United States

The global crude oil and stock markets have been extremely volatile in recent years, with prices fluctuating rapidly. We considered the linkages between the crude oil market and the stock market in China and the US, applying a time-varying t-Copula-GARCH model based on the Chinese INE crude oil futures price and the SSEC, and American WTI crude oil futures price and the S&P 500. We found that there are positive correlations between crude oil and stock markets in both China and the United States. Although the linkages between the two markets are weaker in China than in the United States, the magnitude of the changes and the volatility are larger. In addition, the linkages between the two markets in China and the U.S. increase significantly under extreme risk events such as the COVID-19 pandemic. These findings enrich the research on the linkages between commodity and stock markets.

A new secondary decomposition-reconstruction-ensemble approach for crude oil price forecasting

This study proposes a new method for crude oil future price forecasting. The original crude oil futures price series is decomposed into a series of sub-sequences using the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) method, and the permutation entropy (PE) method is employed to reconstruct these sub-sequences into high-frequency, low-frequency, and trend components. Using the kernel extreme learning machine (KELM) optimised by the chaotic sparrow search algorithm (CSSA), the low-frequency component and trend component are predicted. However, the high-frequency component is decomposed secondary to the empirical mode decomposition (EMD) method, and the PE and CSSA-KELM models are employed again to obtain the linear integrating prediction result for the high-frequency component. Finally, the forecasting results of the high-frequency, low-frequency, and trend components are nonlinearly integrated with the CSSA-KELM model, and the final forecasting value for crude oil futures prices is obtained. To verify the effectiveness of the proposed model, we empirically forecast the Brent and WTI crude oil futures prices. The empirical results show that the approach proposed in this study improves forecasting accuracy compared to other benchmark models and has good robustness.

Arbitrage breakdown in WTI crude oil futures: An analysis of the events on April 20, 2020

This study provides novel analysis of the events in the WTI crude oil futures market on April 20, 2020. We detail how the arbitrage linkages between the NYMEX CL contract and the e-mini NYMEX QM contract broke down and report new information about the unusual market conditions on that date. After establishing that most price discovery happens in the more liquid CL contract, we show how these two contracts decoupled in the May 2020 spot period. Next, using supervisory CFTC data, we document that the typical arbitragers did not participate in the WTI crude oil markets on April 20. This change in the composition of arbitragers had important implications for the unusual settlement prices in the CL contract. Third, we use generalizable non-parametric methods to rank the values observed in terms of price deviations, realized volatility and spreads to similar crude oils. We find the May 2020 spot month to have the largest values of these measures across all spot periods from 2011 to 2020. Finally, we show that natural gas futures markets did not experience a similar price decoupling, suggesting the lack of storage capacity at Cushing played an important role in the WTI crude negative price event.

Role of Crude Oil Futures in Financial Portfolios under Financialization

This article analyzes the changes in the roles of crude oil futures in financial portfolios due to financialization. To examine the changes, we propose a new dynamic market model between stock and crude oil futures prices, and a new dynamic allocation model of optimal portfolios, by considering the impact of financialization on crude oil markets. Our results show that before crude oil financialization, the optimal positions in S&P 500 varied with time, while those in WTI and Brent crude oil futures stayed almost at the same levels, implying diversification effects from crude oil futures for financial assets. However, after the financialization, the optimal positions of crude oil, particularly WTI futures, decreased chronologically. The parallel shifts of long S&P 500 and short crude oil futures positions may suggest the realization of cash and carry strategies using crude oil futures instead of S&P 500 futures. The role of crude oil futures in financial portfolios can change from diversification to cash and carry arbitrage due to financialization.

Time-varying spillover effects and investment strategies between WTI crude oil, natural gas and Chinese stock markets related to belt and road initiative

This paper investigates the return volatility spillover effects and the dynamic relationships among WTI crude oil futures, Natural Gas futures, and the Chinese stock markets related to Belt and Road initiative employing the method of Diebold and Yilmaz (2012, 2014) based on TVP-VAR model and generalized forecast error variance decomposition. Our empirical results show that there exists a high interdependence among all analyzed assets, and the total volatility spillover has a sharp increase under the major crisis events. On average, WTI, GAS and the stock markets of FM, AGR and COM are the net receivers of systematic shocks, while the stock markets of EU, HSR and INF are the net transmitters of systematic shocks. Besides, we also calculate the hedge ratios, the optimal portfolio weights and the corresponding hedging effectiveness based on DCC-GARCH t-copula model. We find that WTI crude oil and Natural Gas futures are cheap hedging tools. When investing a small part in WTI crude oil future market and a large part in the analyzed stock markets, or investing a small part in the analyzed stock markets and a large part in Natural Gas future market, high hedging effectiveness could be achieved.

Predicting the price of WTI crude oil futures using artificial intelligence model with chaos

This paper mainly investigates the chaotic features as well as prediction of WTI crude oil daily price time series from January 02, 2009 to November 25, 2019 with chaos theory and Artificial Intelligence technology, and analyzes the influence of noise on the price forecast.Firstly, we judge whether there is chaos in the time series of crude oil futures price by calculating the largest Lyapunov exponent, and applying Bootstrap technique to verify the robustness of the largest Lyapunov exponent. Secondly, we construct eight models with ANN technology and Chaos theory to fit the data and make short-term prediction. We find that the forecast accurateness can be improved dependent on the intrinsic formation mechanism (chaotic) model and removing noise can enhance the prediction accuracy of the model. Accurate prediction of WTI crude oil futures price is of high return for investors, low risk for risk management, and effective regulation of financial market for government departments. Finally, it is concluded that the EMD-LR-CHAOS model appeared to be the best prediction model among the eight models. As a first step, we calculate the greatest Lyapunov exponent and use the Bootstrap technique to test its robustness.