Oil Price Forecasting Research Articles

Crude oil price forecasting with multivariate selection, machine learning, and a nonlinear combination strategy

Crude oil price forecasting has been one of the research hotspots in the field of energy economics, which plays a crucial role in energy supply and economic development. However, numerous influencing factors bring serious challenges to crude oil price forecasting, and existing research has room for further improvement in terms of an integrated research roadmap that combines impact factor analysis with predictive modelling. This study aims to examine the impact of financial market factors on the crude oil market and to propose a nonlinear combined forecasting framework based on common variables. Four types of daily exogenous financial market variables are introduced: commodity prices, exchange rates, stock market indices, and macroeconomic indicators for ten indicators. First, various variable selection methods generate different variable subsets, providing more diversity and reliability. Next, common variables in the subset of variables are selected as key features for subsequent models. Then, four models predict crude oil prices using common features as inputs and obtain the prediction results for each model. Finally, the nonlinear mechanism of the deep learning technology is introduced to combine above single prediction results. Experimental results reveal that commodity and foreign exchange factors in financial markets are critical determinants of crude oil market volatility over the long term, as observed in experiments conducted on the West Texas Intermediate and Brent oil price datasets. The proposed model demonstrates strong performance regarding average absolute percentage error, recorded at 2.9962% and 2.4314%, respectively, indicating high forecasting accuracy and robustness. This forecasting framework offers an effective methodology for predicting crude oil prices and enhances understanding the crude oil market.

Oil-price forecasting based on ARIMA, exponential smoothing, and autoregressive neural network models

Oil prices have an impact on the global economy. Demand shocks, such as those caused by the recent COVID-19 epidemic, or supply shocks caused by production reductions by major global producers, result in sudden price changes. Oil industry has been collecting price data since the late 19th century. A time series of this magnitude allows for consistent analysis of price behavior forecasts following demand or supply shocks. Financial time series are sensitive to exogenous shocks. From this perspective, this work presents a comparative analysis of predictive crude oil prices scenarios, obtained from a historical series of average annual prices. Two approaches were used: first, a combination of classic strategies based on exponential smoothing, and ARIMA models. Second, an autoregressive neural network model. Both approaches are complementary when used for long-term forecasting of oil prices and show good response to volatile data. Therefore, we are able to present an alternative data analysis, in a field where there is a great amount of relevant historical series, using probabilistic and non-linear models in order to observe predictions and make more effective decisions.

Intelligent crude oil price probability forecasting: Deep learning models and industry applications

The crude oil price has been subject to periodic fluctuations because of seasonal changes in industrial demand and supply, weather, natural disasters and global political unrest. An accurate forecast of crude oil prices is of utmost importance for decision makers and industry players in the energy sector. Despite this, the volatility of crude oil prices contributes to the uncertainty of the energy industry, which was particularly challenging following the recent global spread of the COVID-19 epidemic and the Russia–Ukraine conflict. This paper proposes a hybrid deep learning (DL) modelling framework to deal with the volatility of crude oil prices, applying ensemble empirical mode decomposition (EEMD), convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) integrated with quantile regression (QR); named EEMD-CNN-BiLSTM-QR. Two real-world datasets on crude oil prices from the West Texas Intermediate and Brent Crude Oil markets were employed to validate the EEMD-CNN-BiLSTM-QR hybrid modelling framework. Given that the probability density forecast can capture uncertainty, an in-depth analysis was carried out and prediction accuracy calculated. The findings of this study demonstrate that the proposed EEMD-CNN-BiLSTM-QR DL modelling framework, which uses the probability density forecast method, is superior to other tested models in terms of its ability to forecast crude oil prices. The novelty of this study stems mainly from its use of QR, which allows for the description of the conditional distribution of predicted variables and the extraction of more uncertain information for probability density forecasts.

Enhancing Multi-step Brent Oil Price Forecasting with Ensemble Multi-scenario Bi-GRU Networks

Accurate crude oil price forecasting is crucial for economic stability, investment planning, and strategic decision-making across various industries. Despite numerous research efforts in applying deep learning to time-series forecasting, achieving high accuracy in multi-step predictions for volatile time-series like crude oil prices remains a significant challenge. Moreover, most existing approaches primarily focus on one-step forecasting, and the performance often varies depending on the dataset and specific case study. This paper introduces ensemble-based deep-learning models to capture Brent oil price volatility and enhance the multi-step price prediction. Our methodology employs a two-pronged approach. First, we present an empirical comparison of deep-learning models and architectures, including RNNs, CNNs, and transformers, for forecasting Brent oil prices. We also examine the impact of various external factors on forecasting accuracy. Then, we introduce a novel approach that employs ensemble GRU-based models to enhance prediction accuracy across multiple forecasting scenarios. Extensive experiments were conducted using a dataset of historical Brent prices encompassing the COVID-19 pandemic, which significantly impacted energy markets. The results demonstrate that the proposed model outperforms benchmark and established models, achieving a 9.3% reduction in MSE compared to the closest benchmark model for a 3-day forecasting horizon.

A novel link prediction model for interval-valued crude oil prices based on complex network and multi-source information

Accurate crude oil price forecasting is crucial for maintaining energy economy stability and enhancing investment and operational decision-making. Nowadays, the link prediction model for crude oil prices based on a complex network model has become an emerging and promising approach. However, existing link prediction methods are unable to extract complex information about interval-valued crude oil prices, and fail to consider the impact of multi-source information. Therefore, this paper proposes the link prediction model for interval-valued crude oil prices using complex network and multi-source information, which converts crude oil price interval series into complex networks. Through link prediction, it takes into account both the impact of past interval-crude oil prices on future interval time series and the interference of external real-time information on interval-valued prices. First, news headlines and geopolitical risk indices related to crude oil prices are captured, and search index data and news sentiment scores associated with interval data are analyzed. Subsequently, the interval sequence data and related influencing factors are decomposed and reconstructed respectively. The reconstructed interval center and radius sequence are then converted into a directed network, and node similarity in the network is calculated to generate similar nodes of the interval subsequence as feature values. Finally, multiple machine learning models are employed to acquire the optimal weighted combination prediction with interval prediction values. According to the experimental data, this approach outperforms other benchmark methods in terms of prediction accuracy.

Application of Logistic Model in International Oil Price Forecasting and Analysis of Sudden Factors

Application of Logistic Model in International Oil Price Forecasting and Analysis of Sudden Factors

Crude oil price forecasting using K-means clustering and LSTM model enhanced by dense-sparse-dense strategy

Crude oil is an essential energy source that affects international trade, transportation, and manufacturing, highlighting its importance to the economy. Its future price prediction affects consumer prices and the energy markets, and it shapes the development of sustainable energy. It is essential for financial planning, economic stability, and investment decisions. However, reaching a reliable future prediction is an open issue because of its high volatility. Furthermore, many state-of-the-art methods utilize signal decomposition techniques, which can lead to increased prediction time. In this paper, a model called K-means-dense-sparse-dense long short-term memory (K-means-DSD-LSTM) is proposed, which has three main training phrases for crude oil price forecasting. In the first phase, the DSD-LSTM model is trained. Afterwards, the training part of the data is clustered using the K-means algorithm. Finally, a copy of the trained DSD-LSTM model is fine-tuned for each obtained cluster. It helps the models predict that cluster better while they are generalizing the whole dataset quite well, which diminishes overfitting. The proposed model is evaluated on two famous crude oil benchmarks: West Texas Intermediate (WTI) and Brent. Empirical evaluations demonstrated the superiority of the DSD-LSTM model over the K-means-LSTM model. Furthermore, the K-means-DSD-LSTM model exhibited even stronger performance. Notably, the proposed method yielded promising results across diverse datasets, achieving competitive performance in comparison to existing methods, even without employing signal decomposition techniques.

Advanced Machine Learning Techniques for Accurate Forecasting of Crude Palm Oil Price

Advanced Machine Learning Techniques for Accurate Forecasting of Crude Palm Oil Price

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.

The Impact of Oil Prices on the GDP of V4 Countries

This study is concerned with forecasts of GDP growth for the Visegrad countries (V4-hereafter) and oil prices simultaneously. The series for GDP and Oil prices are quarterly, covering the period from December 1, 2000, to October 1, 2023. Neural network techniques were performed to generate individual forecasts. The forecasts for oil prices maintain higher accuracy than the GDP ones due to autoregressive lags. In other words, current oil prices absorb significant influence from past prices. The GDP forecasts for the V4 group indicate tremendous shock and moving growth to a lower steady state. The lower growth observed by the end of the period under review can be attributed to two subsequent non-economic shocks: the Russia-Ukraine war and the COVID-19 pandemic. The V4 countries faced difficulties after the outbreak of COVID-19, mainly due to the stringency measures. In addition to accelerating inflation, the war also disrupted energy commodities within supply chains. These and other facts justify the low growth that awaits these countries until 2028. Ultimately, the oil price until 2028 is estimated to oscillate between $60 and $90 per barrel.

Navigating the Dynamics of Brent Crude Oil Prices: Factors, Trends, and Insights

Accurate Brent Crude Oil price prediction is essential for informed decision-making and risk control in the global energy market. This paper examines the dynamics of Brent Crude Oil prices over the previous 35 years, utilizing predictive modelling techniques to project future prices and analyzing historical trends and relationships with the GDPs of major economies. The statistical methods used in this paper include the moving average and Pearson correlation coefficient. While correlation studies show significant positive links between Brent Crude Oil prices and the GDPs of major economies like China, Saudi Arabia, Europe, Russia, and the United States, historical data analysis reveals large price volatility. Highly accurate price forecasting using LSTM (Long Short-Term Memory) modelling approaches provides detailed risk management and decision-making information in the global energy market. The application of the Neural Network and the ARIMA model shows an increase in the price of Brent crude oil in the next year, 2024. Identifying the importance of the Brent crude oil price forecast and its effect on the international market is highly needed. This paper thus might help to increase economic growth. These results highlight the importance of advanced modelling techniques and economic indicators in managing oil price changes and help make informed decisions in the energy industry.

A multiscale time-series decomposition learning for crude oil price forecasting

Crude oil price forecasting is important for market participants and policymakers. However, accurately tracking oil prices is quite a challenging task due to the complexity of temporal oil data and the nonlinear relationships involved in the forecasting task. In this study, a multiscale time-series decomposition learning framework is proposed to deal with this issue. First, a multiscale temporal processing module is designed to capture different frequency time-series patterns in historical data at various scales. Then, a multiscale decomposition technique is applied to decompose historical crude oil data into various temporal modes, involving global shared information across multiple scales, as well as local specific information that varies at each scale. Finally, a multiscale fusion mechanism is employed to combine these information, which are further used as inputs to construct nonlinear and complex predictive models for crude oil prices. A series of experiments conducted on Shanghai crude oil market demonstrate that the proposed approach outperforms several econometric and machine learning models.

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.

Forecasting interval‐valued returns of crude oil: A novel kernel‐based approach

AbstractThis paper proposes a novel kernel‐based generalized random interval multilayer perceptron (KG‐iMLP) method for predicting high‐volatility interval‐valued returns of crude oil. The KG‐iMLP model is constructed by utilizing the distance based on a kernel function, which outperforms the conventional Euclidean distance. Additionally, the optimal kernel function is estimated using the variance–covariance matrix of the prediction error, contributing to a better understanding of the overall characteristics of interval‐valued data. The introduction of the kernel function renders the algorithms used for estimating machine learning parameters ineffective. Therefore, this paper further proposes a backward distance of accumulative error propagation algorithm to estimate both the kernel function and model parameters, which provides a feasible approach for utilizing kernel function in interval neural networks. In the empirical analysis of weekly and daily returns of WTI crude oil, the superior predictive performance of the proposed method is demonstrated, enabling stable and accurate predictions for both point values and interval values. The model exhibits consistent outstanding performance across different network structures, showcasing the potential of KG‐iMLP for crude oil price forecasting.

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

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.

Predicting crude oil prices using SARIMA-X method: An empirical study

Crude oil prices wield substantial influence over economic stability and sustainability, exerting a profound impact across various sectors and significantly moulding the economic well-being of nations. Thus, precision of predicting crude oil prices is of utmost importance for a wide array of stakeholders, including policymakers, investors, and participants in the energy market. This study offers an empirical exploration of the Seasonal Autoregressive Integrated Moving Average with Exogenous Variables (SARIMA-X) method, employing RMSE and MAPE values for forecasting crude oil prices during the most volatile periods from 2020 to 2023, including both COVID-19 pandemic and Russia Ukraine war period. The results indicate that the SARIMA-X method is effective for predicting crude oil prices during turbulent market conditions. This model can be a valuable tool for investors, traders, and other market participants, enabling them to make informed decisions when it comes to both intraday trading and long-term forecasting of crude oil prices.

Do oil price forecast disagreement of survey of professional forecasters predict crude oil return volatility?

This paper explores whether the dispersion in forecasted crude oil prices from the European Central Bank Survey of Professional Forecasters can provide insights for predicting crude oil return volatility. It is well-documented that higher disagreement among forecasters of asset price implies greater uncertainty and higher return volatility. Using several Generalized Autoregressive Conditional Heteroskedasticity with Mixed Data Sampling (GARCH-MIDAS) models, we find, based on the in-sample estimation results, the oil market experiences greater volatility when the forecasters’ disagreements increase. The model that integrates both historical realized variance and forward-looking forecaster disagreement into the conditional variance, along with the model focusing solely on pure forward-looking forecaster disagreement, exhibits a much superior fit to the data compared to the model relying solely on realized variance and the models considering forward-looking forecasted mean return. The out-of-sample forecasting results unequivocally illustrate that incorporating forecaster disagreement offers valuable insights, markedly enhancing the predictive accuracy of crude oil return volatility within the GARCH-MIDAS model. Moreover, we illustrate the economic benefit of considering forecasters’ disagreement when forecasting volatility, demonstrating its significance for VaR risk management.

The main approaches to valuation of the equity capital of oil and gas companies

Subject. This article analyzes the generally accepted approaches to assessing the value of companies on the basis of financial statements data of ExxonMobil, Chevron, ConocoPhillips, Occidental Petroleum, Devon Energy, Anadarko Petroleum, EOG Resources, Apache, Marathon Oil, Imperial Oil, Suncor Energy, Husky Energy, Canadian Natural Resources, Royal Dutch Shell, BP, TOTAL, Eni, Equinor (Statoil), PetroChina, Sinopec, CNOOC, Petrobras, PJSC Gazprom, PJSC NK Rosneft and PJSC LUKOIL for 1999–2018. Objectives. The article aims to determine the specifics of using the methods of cost, income and comparative approaches in assessing the value of share capital of oil and gas companies. Methods. For the study, I used the methods of comparative, and financial and economic analyses, and financial reporting data summarizing. Results. The article finds that the cost approach is quite time-consuming, and it does not take into account the current market situation and future expectations of investors, but is based on financial information. Leading oil and gas corporations have a rather complex vertical and horizontal structure, so the cost approach is acceptable for assessing the minimum cost of small companies in the industry. The income approach takes into account the interests of investors, but its application complicates the reliability of medium-term forecasts for oil prices, which is caused by fluctuations in oil prices inherent in the industry. And the amount of net income and free cash flow in the industry largely depends on oil prices. The comparative approach does not take into account the future interests of investors, but it helps quickly determine the range of possible value of the corporation based on data on transactions and the current market situation. Thus, the analogue company method helps evaluate the cost of equity capital, and the transaction method provides insight into the level of premium for control characteristic of the industry. Conclusions and Relevance. Each of the standard approaches has its own characteristic advantages and disadvantages when assessing the value of oil and gas companies. The findings can be used to appraise the value of oil and gas assets.

A new feature selection method based on importance measures for crude oil return forecasting

This paper introduces a novel feature selection method, called Feature Selection based on Importance Measures (FS-IM), to enhance the forecasting of crude oil returns. FS-IM innovatively combines active learning with the application of Gaussian noise to input features and selects the most relevant features using an optimal threshold value. The paper applies a ridge regression (RR) model based on FS-IM (FS-RR) to identify the factors that have important information for crude oil return forecasting. The paper compares FS-IM with other dimension reduction methods such as Principal Component Analysis (PCA), Kernel Principal Component Analysis (KPCA), and Independent Component Analysis (ICA). The results show that FS-IM can significantly improve model accuracy, demonstrating its effectiveness in finding key features. Moreover, FS-IM is more stable and consistent than other dimension reduction methods in enhancing the prediction accuracy in different scenarios, indicating its superior capability in capturing complex relationships between input and output variables. Furthermore, this study compares FS-RR model with other 13 prediction models by conducting experiments using a series of evaluation metrics, different statistical tests, and different step-ahead predictions and training sets. The results confirm that the RR model based on FS-IM can consistently outperform other model in terms of predictive performance and economic value, proving its effectiveness and robustness. This study contributes to the literature on crude oil price forecasting by addressing the challenges of high-dimensional and complex data, and by providing a robust, practical tool for professionals in energy economics and finance.

Evaluating Oil Price Forecasts: A Meta-analysis

Oil price forecasts have traditionally attracted the interest of both the empirical literature and policy makers, although research efforts have been intensified in the last 15 years. The present study investigates the forecasting characteristics that have the greatest impact on the accuracy level of such forecasts. To achieve this, we employ a meta-analysis approach of more than 6,000 observations of relative root mean squared errors (RRMSEs) which are pooled within a Bayesian Model Averaging (BMA) method. The findings indicate that forecasting frameworks such as MIDAS and combined forecasts tend to report significantly lower forecast errors. In addition, the choice of the oil price benchmark is an important factor, with the Brent price to offer lower forecast errors. Furthermore, the short-run horizons tend to produce more accurate forecasts and the same holds for the real, instead of the nominal oil prices. A number of robustness tests confirms the validity of these results. Overall, the findings of this study serve as a guide for future oil price forecasting exercises.