Volatility Of Crude Oil Futures Research Articles

Forecasting realized volatility of crude oil futures prices based on machine learning

AbstractExtending the popular HAR model with additional information channels to forecast realized volatility of WTI futures prices, we show that machine learning‐generated forecasts provide better forecasting quality and that portfolios that are constructed with these forecasts outperform their competing models resulting in economic gains. Analyzing the selection process, we show that information channels vary across forecasting horizon. Variable selection produces clusters and provides evidence that there are structural changes with regard to the significance of information channels.

Forecasting the volatility of crude oil futures: A time‐dependent weighted least squares with regularization constraint

AbstractParameter instability and model uncertainty are two key problems affecting forecasting outcomes. In this paper, we propose a time‐dependent weighted least squares with ridge constraint (TWLS‐Ridge) to solve the above two problems in the forecasting procedure. The new TWLS‐Ridge approach is applied to the heterogenous autoregressive realized volatility model and its various extensions. The empirical results suggest that TWLS‐Ridge produces more accurate volatility forecasts than several alternative models dealing with parameter instability and model uncertainty. The superior performance of TWLS‐Ridge is robust under different forecast horizons, evaluation periods, and loss functions. An investor with mean–variance preference can improve utility using TWLS‐Ridge forecasts of oil volatility instead of ordinary least squares model forecasts.

Exploring the relationship between global economic policy and volatility of crude futures: A two-factor GARCH-MIDAS analysis

This study investigates the impact of global economic policy on the volatility of crude oil futures using a two-factor GARCH-MIDAS (Mixed Data Sampling) analysis. The core of the problem statement is the need to understand how global economic policy affects the volatility of crude oil futures, which has significant implications for investors, decision-makers, and market participants. The study aims to determine the correlation between critical global economic policy variables and crude oil futures volatility. This study combines the Generalized Autoregressive Conditional Heteroscedasticity (GARCH) framework and the Mixed Data Sampling (MIDAS) method to create a Two-Factor GARCH-MIDAS model. This model thoroughly analyzes the long- and short-term dynamics between economic policy and crude oil futures volatility by incorporating macroeconomic and financial market data. The analysis covers a specific period from 2010 to 2021 and considers both prosperous and challenging economic times. The study's narrow geographic focus on a region with significant global economies and oil markets ensures a thorough representation of monetary and fiscal policies and changes in crude oil futures prices. The analysis provided insight into the complex link between volatility in crude oil futures and global economic policy. The results provide insightful information about how changes in interest rates, fiscal policies, and trade regulations affect the volatility of crude oil futures. The study advances knowledge of the connections between economic policy and energy markets, enabling investors and decision-makers in the international oil market to make more informed choices.

The role of global economic policy uncertainty in predicting crude oil futures volatility: Evidence from a two-factor GARCH-MIDAS model

The fluctuations in global policy affect the volatility of international crude oil markets. It is quite meaningful to analyze the impact of policy uncertainty on crude oil market volatility from a global integration perspective in deep. This paper aims to examine whether the global uncertainty of economic policy (GEPU) and the uncertainty of uncertainty (GEPU change) have different impacts on crude oil futures volatility. We establish two types of models under the GARCH-MIDAS framework, single-factor model and two-factor model, for discussing their explanatory and predictive power when considering the historical realized volatility. The findings show the GEPU index and its changes are consistent effective predictive factors in volatility of crude oil futures market when only individual effect is considered. Specially, GEPU change has stronger predictive power than GEPU index. Furthermore, the two-factor model with GEPU change contains more information which holds stronger forecasting ability in crude oil futures market volatility. However, GEPU cannot be an effective forecast factor when taking the influence of realized volatility into account.

The role of uncertainty measures in volatility forecasting of the crude oil futures market before and during the COVID-19 pandemic

The purpose of this article is to investigate whether various uncertainty measures provide incremental information for the prediction the volatility of crude oil futures under high-frequency heterogeneous autoregressive (HAR) model specifications. Moreover, by considering the information overlap among various uncertainty measures and fully using of the information in various uncertainty measures, this paper uses two prevailing shrinkage methods, the least absolute shrinkage and selection operator (lasso) and elastic nets, to select uncertainty variables during the entire sampling period, before the COVID-19 pandemic and during the COVID-19 pandemic and then uses the HAR model to predict crude oil volatility. The results show that (i) uncertainty measures can be utilized to predict crude oil volatility under the high-frequency framework in both in-sample and out-of-sample analyses. (ii) Because of the information overlap between various uncertainty measures, adding a large number of uncertain variables to the HAR model may not significantly improve the volatility prediction. (iii) Before and during the COVID-19 pandemic, Chicago Board Options Exchange (CBOE) crude oil volatility (OVX) has the greatest impact on crude oil volatility, infectious disease equity market volatility (EMV) exerts a significant influence on crude oil futures volatility forecasts during the COVID-19 period, and CBOE implied volatility (VIX) and the financial stress index (FSI) have substantial impacts on crude oil futures volatility forecasts before COVID-19.

Volatility and Asymmetric Effect of Crude Oil Options on Crude Oil Market: Empirical Evidence from China

Based on daily data, this paper uses the GARCH model family to empirically study the impact of crude oil option launch on the volatility and asymmetric leverage effect of crude oil futures market variables (futures price, trading volume, open interest, inventory).The conclusion is as follows: Regardless of the impact of the COVID-19, the launch of crude oil options has a long-term volatility impact on price, open interest and inventory volatility in addition to trading volume, and only has a long-term volatility impact on prices under the influence of COVID-19.Regardless of whether the impact of COVID-19 is considered, the launch of crude oil options has intensified the volatility of price yield, reduced the volatility of trading volume, open interest and inventory, and Considering COVID-19 influence, the volatility of crude oil futures prices yield has weakened, and the degree of weakening of trading volume fluctuations has decreased. Regardless of the impact of COVID-19, crude oil futures prices, trading volume, open interest, and inventory volatility all have negative asymmetric leverage effects, and the impact of bearish news is greater than the impact of bullish news. Considering the introduction of crude oil options under the influence of COVID-19: the fluctuation of crude oil futures prices yield has changed from negative asymmetry to positive asymmetric leverage effect. The asymmetric leverage effect of negative fluctuations in crude oil futures trading volume becomes smaller and decreases less than the leverage effect without considering the impact of COVID-19 after the listing of crude oil options. Fluctuations in open interest and inventory have weakened the negative asymmetric leverage effect after the launch of crude oil options. Finally, relevant policy suggestions are given for the construction of the domestic options market.

Forecasting the volatility of crude oil futures: The role of oil investor attention and its regime switching characteristics under a high-frequency framework

The purpose of this article is to investigate whether oil investor attention (OA), measured by Google search volume, contains incremental information content to predict crude oil futures volatility under high-frequency heterogeneous autoregressive (HAR) model specifications. Moreover, to account for possible structural breaks and nonlinearity in the relation between OA and crude oil volatility, this article extends HAR-type models with regime switching considerations. The results of parameter estimation and out-of-sample prediction show that the in-sample and out-of-sample performance of HAR-type and Markov switching (MS)-HAR-type models with OA is significantly better than that of their corresponding HAR-type and MS-HAR-type models without OA. Furthermore, our findings suggest that (i) HAR-type-OA models tend to produce better forecasts for the volatility of the crude oil market at short horizons (1-day) compared to HAR-type, MS-HAR-type and MS-HAR-type-OA models. (ii) MS-HAR-type-OA models have the best forecasting performance at relatively long prediction horizons (1-week and 1-month). Therefore, the result suggests that the OA and regime switching specifications have a significant positive impact on volatility predictions and can be useful for improving the performance of HAR-type models.

Volatility forecasting of crude oil futures based on a genetic algorithm regularization online extreme learning machine with a forgetting factor: The role of news during the COVID-19 pandemic

The outbreak of news and opinions during the COVID-19 pandemic is unprecedented in this age of rapid dissemination of information. The ensuing uncertainty has led to the emergence of heightened volatility in prices of crude oil futures. Whether such news has predictive value for the volatility of crude oil futures during the COVID-19 pandemic is examined in this research. We proposed a modeling framework, genetic algorithm regularization online extreme learning machine with forgetting factor (GA-RFOS-ELM), to estimate the effects of news during the COVID-19 pandemic on the volatility of crude oil futures. GA-RFOS-ELM could learn block-by-block with fixed or varying block size when considering the block own valid period. The experimental results illustrate that news during the COVID-19 pandemic has more predictive information, which is crucial for short-term volatility forecasting of crude oil futures. The novel approach illustrates that online update learning ability is needed during the COVID-19 pandemic, which could be effective and efficient in volatility forecasting of crude oil futures. The contributions of our study are significant for investors and administrators to predict and understand the behavior of volatility during the COVID-19 pandemic.

Forecasting volatility of crude oil futures using a GARCH–RNN hybrid approach

AbstractVolatility is an important element for various financial instruments owing to its ability to measure the risk and reward value of a given financial asset. Owing to its importance, forecasting volatility has become a critical task in financial forecasting. In this paper, we propose a suite of hybrid models for forecasting volatility of crude oil under different forecasting horizons. Specifically, we combine the parameters of generalized autoregressive conditional heteroscedasticity (GARCH) and Glosten–Jagannathan–Runkle (GJR)‐GARCH with long short‐term memory (LSTM) to create three new forecasting models named GARCH–LSTM, GJR‐LSTM, and GARCH‐GJRGARCH LSTM in order to forecast crude oil volatility of West Texas Intermediate on different forecasting horizons and compare their performance with the classical volatility forecasting models. Specifically, we compare the performances against existing methodologies of forecasting volatility such as GARCH and found that the proposed hybrid models improve upon the forecasting accuracy of Crude Oil: West Texas Intermediate under various forecasting horizons and perform better than GARCH and GJR‐GARCH, with GG–LSTM performing the best of the three proposed models at 7‐, 14‐, and 21‐day‐ahead forecasts in terms of heteroscedasticity‐adjusted mean square error and heteroscedasticity‐adjusted mean absolute error, with significance testing conducted through the model confidence set showing that GG–LSTM is a strong contender for forecasting crude oil volatility under different forecasting regimes and rolling‐window schemes. The contribution of the paper is that it enhances the forecasting ability of crude oil futures volatility, which is essential for trading, hedging, and purposes of arbitrage, and that the proposed model dwells upon existing literature and enhances the forecasting accuracy of crude oil volatility by fusing a neural network model with multiple econometric models.

Predicting the volatility of crude oil futures: The roles of leverage effects and structural changes

AbstractThis paper investigates whether leverage effects and structural changes have positive effects on the volatility prediction of crude oil futures. On the basis of existing HAR models, this paper proposes three classes of new HAR models by considering leverage effects, structural changes, or both. The in‐sample and out‐of‐sample results show that leverage effects and structural changes contain significant information for predicting oil volatility. In most cases, structural changes have more in‐sample and out‐of‐sample incremental information than leverage effect, whereas leverage effects have more out‐of‐sample information for predicting 1‐day volatility. In addition, HAR models with leverage effects and structural changes have better in‐sample and out‐of‐sample performances than the corresponding other three classes of HAR models. The above results mean that leverage effects and structural changes should be considered while modelling and forecasting oil volatility.

The role of intermediary capital risk in predicting oil volatility

AbstractThis paper aims to investigate the ability of market‐based intermediary capital risk to predict the volatility of crude oil futures. Using shocks to the market‐based intermediary capital ratio (IC_RF) of primary dealers as a predictor, this paper shows that IC_RF exhibits statistically and economically significant predictive power for the volatilities of crude oil futures, from both in‐sample and out‐of‐sample perspectives. The revealed predictability is also of economic significance, because it enables examining of the performance of portfolios that are constructed on IC_RF‐based forecasts of oil volatility. Additionally, IC_RF contains robust predictive power beyond what is embedded in traditional fundamental variables. Further analysis provides solid evidence supporting the superiority of asymmetric and regime change models over linear specifications in forecasting oil realized volatility, and it only provides weak evidence for implied oil volatility.

On realized volatility of crude oil futures markets: Forecasting with exogenous predictors under structural breaks

We introduce Infinite Hidden Markov (IHM) models to forecasting realized volatilities of crude oil futures markets with exogenous factors. With these IHM models, we lift the restriction of a pre-defined number of regimes and allow for an unknown number of different parameter regimes and breakpoints. We employ two types of infinite hidden Markov models to accommodate structural breaks incurred by policy changes, exogenous shocks, and other factors. We find that IHM-HAR models outperform all other non-switching variants. In regard to forecasting performance, IHM-HAR models with exogenous factors such as realized volatilities of competing futures markets and the S&P500 are superior model choices for short-term forecasts. For longer-term forecasts, the equity channel shows only little positive impact. Evidence of economic gains in portfolio construction based on IHM-HAR forecasts is provided. • Infinite Hidden Markov (IHM) models are introduced to forecasting crude oil realized volatility. • IHM models lift the restriction of a pre-defined number of possible regimes. • IHM-HAR models outperform all other non-switching variants. • IHM-HAR models with exogenous factors are superior for short-term forecasts. • Portfolio construction based on IHM-HAR models provides economic gains.

Forecasting realized volatility of crude oil futures with equity market uncertainty

ABSTRACTThis paper examines whether the equity market uncertainty (EMU) index contains incremental information for forecasting the realized volatility of crude oil futures. We use 5-min high-frequency transaction data for WTI crude oil futures and develop six heterogeneous autoregressive (HAR) models based on classical HAR-type models. The empirical results suggest that EMU contains more incremental information than the economic policy uncertainty (EPU) for forecasting the realized volatility of crude oil futures. More importantly, we argue that EMU is a non negligible additional predictive variable that can significantly improve the 1-day ahead predictive accuracy of all six HAR-type models, and improve the 1-week ahead forecasting performance of the HAR-RV, HAR-RV-J, HAR-RSV, HAR-RV-SJ models. These findings highlight a strong short-term and a weak mid-term predictive ability of EMU in the crude oil futures market.

The incremental information content of investor fear gauge for volatility forecasting in the crude oil futures market

This paper aims to investigate whether investor fear gauge (IFG) contains incremental information content for forecasting the volatility of crude oil futures. For this purpose, we use oil volatility index (OVX) to measure the IFG. Adding the IFG to existing heterogeneous autoregressive (HAR) models, we develop many HAR models with IFG. Subsequently, we employ these HAR models to predict the volatility of crude oil futures. The results from the parameter estimation and out-of-sample forecasting show that the in-sample and out-of-sample performances of HAR models with IFG are significantly better than their corresponding HAR models without IFG. The results are robust in different ways. Thus, the HAR models with IFG are more beneficial to the decision making of all participants (including financial traders, manufacturers and policymakers) in the crude oil futures market. More importantly, the results suggest that the investor fear gauge has a significant positive effect on volatility forecasting, and can help improve the performances of almost all the existing HAR models.

Is economic policy uncertainty important to forecast the realized volatility of crude oil futures?

ABSTRACTIn this research, we first investigate whether economic policy uncertainty (EPU) index can increase the HAR-RV-type models’ forecast accuracy. In addition, we explore how EPU index can be effectively used to gain larger economic values in the oil futures market. To this end, this research provides a new perspective on setting thresholds for EPU and examines whether these thresholds can help improve both the forecast accuracy and economic values. Empirical results suggest that the HAR-RV-type models including EPU can generate more accurate forecasts and economic values. The HAR-RV-type models including above-threshold EPU can further improve the forecast accuracy and yield higher economic values by setting specific thresholds for a range of horizons. The findings highlight the importance of EPU and effective way of using EPU in risk management and portfolio strategies that is crucial for investors and policymakers.

Forecasting the volatility of crude oil futures using high-frequency data: further evidence

We forecast the realized volatility of crude oil futures market using the heterogeneous autoregressive model for realized volatility and its various extensions. Out-of-sample findings indicate that the inclusion of jumps does not improve the forecasting accuracy of the volatility models, whereas the “leverage effect” pertaining to the difference between positive and negative realized semi-variances can significantly improve the forecasting accuracy in predicting the short- and medium-term volatility. However, the signed jump variations and its decomposition couldn’t significantly enhance the models’ forecasting accuracy on the long-term volatility.

Forecasting the volatility of crude oil futures using HAR-type models with structural breaks

We introduce sixteen HAR-type volatility models with structural breaks and estimate their parameters by applying 5-min high-frequency transaction data for WTI crude oil futures. We find significant structural breaks in the volatility of crude oil futures. Additionally, the historical realized volatility, continuous sample path variation, negative realized semivariance, signed jump, signed semi-jump and leverage components contain substantial and salient information for forecasting the volatility of crude oil futures. Then, we use loss functions to assess the forecasting performance of these sixteen new models, and finally, rank these models using the PROMETHEE II method. Our results indicate that different models exhibit different predictive power in forecasting the 1-day, 1-week and 1-month volatility of crude oil futures. Of the new HAR-type models, the new HAR-RSV model performs best at forecasting the 1-day and 1-month volatilities, whereas the new HAR-CJ best forecasts the 1-week volatility.

Forecasting the volatility of crude oil futures using intraday data

We use the information in intraday data to forecast the volatility of crude oil at a horizon of 1–66days using a variety of models relying on the decomposition of realized variance in its positive or negative (semivariances) part and its continuous or discontinuous part (jumps). We show the importance of these decompositions in predictive (in-sample) regressions using a number of specifications. Nevertheless, an important empirical finding comes from an out-of-sample analysis which unambiguously shows the limited interest of considering these components. Overall, our results indicates that a simple autoregressive specification mimicking long memory and using past realized variances as predictors does not perform significantly worse than more sophisticated models which include the various components of realized variance.

The relationship between Asian equity and commodity futures markets

In this paper, we test spillover effects between Asian equity market volatility and the volatility of the two most dominant commodities, namely, crude oil and gold futures. We consider a total of 14 Asian markets. We find that volatility shocks in established and mature equity markets, such as the Japanese market, spill over to the crude oil and gold futures markets, while immature markets tend to have spillover effects from commodity futures to equity markets. We also report evidence of increased bi-directional volatility transmission during the recent global financial crisis period. Like the volatility of crude oil futures, the volatility of gold futures matters to the equity market. As far as equity market volatility is concerned, the impact of volatility shocks from the gold futures market is as important as the volatility shocks from the crude oil futures market.

The effect of maturity, trading volume, and open interest on crude oil futures price range-based volatility

The determinants of the volatility of crude oil futures prices are examined using an intra-day range-based measure of volatility. The paper employs two distinct approaches: one is to present a contract-by-contract analysis within the sample period, and the second is based on constructed series for the near-month and next-to-near-month contracts over the entire sample period. The contract-by-contract analysis reveals that trading volume and open interest are significant determinants of volatility that dominate the Samuelson maturity effect. The results support earlier findings of a positive and significant role for trading volume, and they also show the importance of open interest in determining volatility, exerting a significant negative effect. The full-period time series analysis also demonstrates the significant role played by open interest in the determination of futures price volatility, further confirming the importance of trading volume.