Forecasting Crude Oil price using Artificial Neural Network model

2021 ◽  
pp. 321-326
Author(s):  
Sivaprakash J. ◽  
Manu K. S.
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Crude Oil ◽  
Back Propagation ◽  
Oil Prices ◽  
Oil Price ◽  
Back Propagation Algorithm ◽  
Crude Oil Price ◽  
Propagation Algorithm ◽  
Crude Oil Prices

In the advanced global economy, crude oil is a commodity that plays a major role in every economy. As Crude oil is highly traded commodity it is essential for the investors, analysts, economists to forecast the future spot price of the crude oil appropriately. In the last year the crude oil faced a historic fall during the pandemic and reached all time low, but will this situation last? There was analysis such as fundamental analysis, technical analysis and time series analyses which were carried out for predicting the movement of the oil prices but the accuracy in such prediction is still a question. Thus, it is necessary to identify better methods to forecast the crude oil prices. This study is an empirical study to forecast crude oil prices using the neural networks. This study consists of 13 input variables with one target variable. The data are divided in the ratio 70:30. The 70% data is used for training the network and 30% is used for testing. The feed forward and back propagation algorithm are used to predict the crude oil price. The neural network proved to be efficient in forecasting in the modern era. A simple neural network performs better than the time series models. The study found that back propagation algorithm performs better while predicting the crude oil price. Hence, ANN can be used by the investors, forecasters and for future researchers.

A New Hybrid Model for Forecasting Crude Oil Price and the Techniques in the Model

2014 ◽  
Vol 974 ◽  
pp. 310-317 ◽  
Author(s):  
Jing Wen Zheng ◽  
Shi Xiao Li ◽  
Yang Kun
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Time Series ◽  
Crude Oil ◽  
Hybrid Model ◽  
Oil Prices ◽  
Oil Price ◽  
Crude Oil Price ◽  
Crude Oil Prices ◽  
Mode Decomposition

Being able to predict crude oil prices with a reputation of intransigence to analysis or the directions of changing in crude oil price is of increasing value. We seek a method to forecast oil prices with precise predictions. In this paper, a hybrid model was proposed, which firstly decomposes the crude oil prices into several time series with different frequencies,then predict these time series which are not white noises, and at last integrate the predictions as the final results. We use Ensemble Empirical Mode Decomposition (EEMD) and Empirical Mode Decomposition (EMD) separately as the technique to decompose crude oil prices. Then we use Dynamic Artificial Neural Network (DAN2) and Back Propagation (BP) Neural Network separately as the technique to predict the deposed time series, and finally integrate the predictions produced by DAN2 or BP by Adaptive Linear Neural Network (ALNN) as the final result of predictions. EEMD has been proved as a very useful method to decompose the nonlinear and non-stationary time series, and DAN2, different from traditional artificial neural networks, also has obvious advantages over traditional ones. In this paper, EEMD and DAN2 are used to predict crude oil prices at the first time。 All in all, we build four models-EEMD-DAN2-ALNN, EMD-BP-ALNN, EEMD-BP-ALNN and EMD-DAN2-ALNN to test which technique, EMD or EEMD, could do better job in decomposition of crude oil prices in this kind of hybrid model and whetherDAN2 could outshine BP when used in this hybrid model. Experimental results of four hybrid models indicate EEMD-DAN2-ALNN could gives the most precise predictions of crude oil prices, and DAN2 has a better performance than traditional neural networks-BP,when used in this hybrid model and EEMD could do a better job than EMD in decomposition of crude oil prices to yield precise predictions of crude oil prices in this model.

scholarly journals Crude Oil Price Forecasting Based on Hybridizing Wavelet Multiple Linear Regression Model, Particle Swarm Optimization Techniques, and Principal Component Analysis

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
Ani Shabri ◽  
Ruhaidah Samsudin
Keyword(s):  
Principal Component Analysis ◽  
Time Series ◽  
Crude Oil ◽  
Oil Prices ◽  
Principal Component ◽  
Oil Price ◽  
Price Forecasting ◽  
Crude Oil Price ◽  
Swarm Optimization ◽  
Crude Oil Prices

Crude oil prices do play significant role in the global economy and are a key input into option pricing formulas, portfolio allocation, and risk measurement. In this paper, a hybrid model integrating wavelet and multiple linear regressions (MLR) is proposed for crude oil price forecasting. In this model, Mallat wavelet transform is first selected to decompose an original time series into several subseries with different scale. Then, the principal component analysis (PCA) is used in processing subseries data in MLR for crude oil price forecasting. The particle swarm optimization (PSO) is used to adopt the optimal parameters of the MLR model. To assess the effectiveness of this model, daily crude oil market, West Texas Intermediate (WTI), has been used as the case study. Time series prediction capability performance of the WMLR model is compared with the MLR, ARIMA, and GARCH models using various statistics measures. The experimental results show that the proposed model outperforms the individual models in forecasting of the crude oil prices series.

scholarly journals An Adaptive Hybrid Learning Paradigm Integrating CEEMD, ARIMA and SBL for Crude Oil Price Forecasting

Energies ◽  
2019 ◽  
Vol 12 (7) ◽  
pp. 1239 ◽  
Author(s):  
Jiang Wu ◽  
Yu Chen ◽  
Tengfei Zhou ◽  
Taiyong Li
Keyword(s):  
Time Series ◽  
Crude Oil ◽  
Prediction Models ◽  
Oil Prices ◽  
Accurate Prediction ◽  
Oil Price ◽  
Crude Oil Price ◽  
Learning Paradigm ◽  
Crude Oil Prices ◽  
Target Values

Crude oil is one of the main energy sources and its prices have gained increasing attention due to its important role in the world economy. Accurate prediction of crude oil prices is an important issue not only for ordinary investors, but also for the whole society. To achieve the accurate prediction of nonstationary and nonlinear crude oil price time series, an adaptive hybrid ensemble learning paradigm integrating complementary ensemble empirical mode decomposition (CEEMD), autoregressive integrated moving average (ARIMA) and sparse Bayesian learning (SBL), namely CEEMD-ARIMA&SBL-SBL (CEEMD-A&S-SBL), is developed in this study. Firstly, the decomposition method CEEMD, which can reduce the end effects and mode mixing, was employed to decompose the original crude oil price time series into intrinsic mode functions (IMFs) and one residue. Then, ARIMA and SBL with combined kernels were applied to predict target values for the residue and each single IMF independently. Finally, the predicted values of the above two models for each component were adaptively selected based on the training precision, and then aggregated as the final forecasting results using SBL without kernel-tricks. Experiments were conducted on the crude oil spot prices of the West Texas Intermediate (WTI) and Brent crude oil to evaluate the performance of the proposed CEEMD-A&S-SBL. The experimental results demonstrated that, compared with some state-of-the-art prediction models, CEEMD-A&S-SBL can significantly improve the prediction accuracy of crude oil prices in terms of the root mean squared error (RMSE), the mean absolute percent error (MAPE), and the directional statistic (Dstat).

scholarly journals Crude Oil Prices Forecasting: An Approach of Using CEEMDAN-Based Multi-Layer Gated Recurrent Unit Networks

Energies ◽  
2020 ◽  
Vol 13 (7) ◽  
pp. 1543 ◽  
Author(s):  
Hualing Lin ◽  
Qiubi Sun
Keyword(s):  
Time Series ◽  
Crude Oil ◽  
Empirical Mode Decomposition ◽  
Oil Prices ◽  
Oil Price ◽  
Crude Oil Price ◽  
Crude Oil Prices ◽  
Mode Decomposition ◽  
Gated Recurrent Unit ◽  
Mode Mixing

Accurate prediction of crude oil prices is meaningful for reducing firm risks, stabilizing commodity prices and maintaining national financial security. Wrong crude oil price forecasts can bring huge losses to governments, enterprises, investors and even cause economic and social instability. Many classic econometrics and computational approaches show good performance for the ordinary time series prediction tasks, but not satisfactory in crude oil price predictions. They ignore the characteristics of non-linearity and non-stationarity of crude oil prices data, which hinder an accurate prediction and eventually lead to poor accuracy or the wrong result. Empirical mode decomposition (EMD) and ensemble EMD (EEMD) solve the problems of non-stationary time series forecasting, but they also generate new problems of mode mixing and reconstruction errors. We propose a hybrid method that is combination of the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and multi-layer gated recurrent unit (ML-GRU) neural network to solve the abovementioned issues. This not only deals with the issue of mode mixing effectively, but also makes the reconstruction error of data close to zero. Multi-layer GRU has an excellent ability of nonlinear data-fitting. The experimental results of real WTI crude oil dataset show that the proposed approach perform better in crude oil prices forecasts than some state-of-the-art models.

scholarly journals Comparative Performance of ARIMA and GARCH Model in Forecasting Crude Oil Price Data

2021 ◽  
pp. 251-275
Author(s):  
Atanu, Enebi Yahaya ◽  
Ette, Harrison Etuk ◽  
Amos, Emeka
Keyword(s):  
Time Series ◽  
Crude Oil ◽  
Moving Average ◽  
Oil Prices ◽  
Oil Price ◽  
Garch Models ◽  
Crude Oil Price ◽  
Autoregressive Integrated Moving Average ◽  
Crude Oil Prices ◽  
Best Fit

This study compares the performance of Autoregressive Integrated Moving Average (ARIMA) and Generalized Autoregressive Conditional Heteroskedasticity models in forecasting Crude Oil Price data as obtained from (CBN 2019) Statistical Bulletin.  The forecasting of Crude Oil Price, plays an important role in decision making for the Nigeria government and all other sectors of her economy. Crude Oil Prices are volatile time series data, as they have huge price swings in a shortage or an oversupply period. In this study, we use two time series models which are Box-Jenkins Autoregressive Integrated Moving Average (ARIMA) and Generalized Autoregressive Conditional Heterocedasticity (GARCH) models in modelling and forecasting Crude Oil Prices. The statistical analysis was performed by the use of time plot to display the trend of the data, Autocorrelation Function (ACF), Partial Autocorrelation Functions (PACF), Dickey-Fuller test for stationarity, forecasting was done based on the best fit models for both ARIMA and GARCH models. Our result shows that ARIMA (3, 1, 2) is the best ARIMA model to forecast monthly Crude Oil Price and we also found GARCH (1, 1) model is the best GARCH model and using a specified set of parameters, GARCH (1, 1) model is the best fit for our concerned data set.

Hybrid of Cuckoo Search Algorithm with Lévy Flight and Neural Network for Crude Oil Prices Prediction

2019 ◽  
Vol 16 (10) ◽  
pp. 4092-4104
Author(s):  
Abdussalam Ya’u Gital ◽  
Mohamed Hamada ◽  
Khalid Haruna ◽  
Mohammed Hassan ◽  
Fatima Shittu ◽  
...  
Keyword(s):  
Neural Network ◽  
Crude Oil ◽  
Search Algorithm ◽  
Oil Prices ◽  
Cuckoo Search ◽  
Cuckoo Search Algorithm ◽  
Convergence Speed ◽  
Oil Price ◽  
Crude Oil Price ◽  
Crude Oil Prices

Accurate prediction of crude oil price can successfully be used to deviate from the negative impact of the crude oil price hike. Limitations of previous studies prompt the proposal of an alternative approach for the hybridization of Cuckoo Search Algorithm with lévy flight and Back-propagation neural network (CSBP) for the estimation of crude oil price to enhance convergence speed accuracy. To evaluate the effectiveness of the proposed CSBP, we used ABC to train BP neural network (ABCNN) and Levenberg-Marquardt neural network (ABCLM) to develop an approach for crude oil price prediction. The outcomes of simulated comparative indicate that the proposed CSBP outperforms the ABCLM and ABCNN in both accuracy and convergence speed. Analysis of variance including post hoc multiple comparative test shows that the performance of the proposed CSBP is statistically significant than the comparison algorithms. The negative side of the crude oil prices in the global market can be defeated with proper planning based on the crude oil prices predicted by the CSBP. The CSBP proposed in this paper could provide a new strategy for risk managers and analysts to create an efficient risk management framework to formulate policies related to risk issues in the global crude oil market.

The optimal thermal causal path analysis on the relationship between international crude oil price and stock market

Kybernetes ◽  
2018 ◽  
Vol 47 (6) ◽  
pp. 1242-1261 ◽  
Author(s):  
Can Zhong Yao ◽  
Peng Cheng Kuang ◽  
Ji Nan Lin
Keyword(s):  
Stock Market ◽  
Crude Oil ◽  
Stock Markets ◽  
Oil Prices ◽  
Oil Price ◽  
Chinese Stock Market ◽  
Crude Oil Price ◽  
Content Type ◽  
Crude Oil Prices ◽  
Causal Path

Purpose The purpose of this study is to reveal the lead–lag structure between international crude oil price and stock markets. Design/methodology/approach The methods used for this study are as follows: empirical mode decomposition; shift-window-based Pearson coefficient and thermal causal path method. Findings The fluctuation characteristic of Chinese stock market before 2010 is very similar to international crude oil prices. After 2010, their fluctuation patterns are significantly different from each other. The two stock markets significantly led international crude oil prices, revealing varying lead–lag orders among stock markets. During 2000 and 2004, the stock markets significantly led international crude oil prices but they are less distinct from the lead–lag orders. After 2004, the effects changed so that the leading effect of Shanghai composite index remains no longer significant, and after 2012, S&P index just significantly lagged behind the international crude oil prices. Originality/value China and the US stock markets develop different pattens to handle the crude oil prices fluctuation after finance crisis in 1998.

scholarly journals Impact of FDI inflow, crude oil prices, and economic growth on CO2 emission in Tunisia: Symmetric and asymmetric analysis through ARDL and NARDL approach

2021 ◽  
Vol 12 (1) ◽  
pp. 1-13
Author(s):  
Tarek Ghazouani
Keyword(s):  
Economic Growth ◽  
Crude Oil ◽  
Carbon Emissions ◽  
Co2 Emission ◽  
Oil Prices ◽  
Oil Price ◽  
Crude Oil Price ◽  
Fdi Inflows ◽  
Crude Oil Prices ◽  
Long Run

This study explores the symmetric and asymmetric impact of real GDP per capita, FDI inflow, and crude oil price on CO2 emission in Tunisia for the 1972–2016 period. Using the cointegration tests, namely ARDL and NARDL bound test, the results show that the variables are associated in a long run relationship. Long run estimates from both approach confirms the validity of ECK hypothesis for Tunisia. Symmetric analysis reveals that economic growth and the price of crude oil adversely affect the environment, in contrast to FDI inflows that reduce CO2 emissions in the long run. Whereas the asymmetric analysis show that increase in crude oil price harm the environment and decrease in crude oil price have positive repercussions on the environment. The causality analysis suggests that a bilateral link exists between economic growth and carbon emissions and a one-way causality ranges from FDI inflows and crude oil prices to carbon emissions. Thus, some policy recommendations have been formulated to help Tunisia reduce carbon emissions and support economic development.

scholarly journals Relationship between International Crude Oil Price and Indian Stock Market (NSE)

2011 ◽  
pp. 63-73
Author(s):  
Rajendra Mahunta
Keyword(s):  
Crude Oil ◽  
Global Economy ◽  
Stock Exchange ◽  
Oil Prices ◽  
Oil Price ◽  
Raw Material ◽  
Crude Oil Price ◽  
New Era ◽  
Crude Oil Prices

In this new era of economic growth, the exceptional increase in the crude oil prices is one of the significant developments that affect the global economy. Crude oil is an important raw material used for manufacturing sectors, so that increase in the price of oil is bound to warn the economy with inflationary inclination. The study examine the long-term relationships between CNX NIFTY FIFTY index of National Stock Exchange and crude price by using various econometric test. The surge in crude oil prices during recent years has generated a lot of interest in the relationship between oil price and equity markets. The study covers the period between 01.01.2010 and 31.12.2014 and was performed with data consisting of 1245 days. The empirical results show there was a cointegrated long-term relationship between CNX index and crude price. Granger causality results reveal that there is unidirectional causality exists and crude oil price causes NSE (CNX) but NSE (CNX) does not cause oil price.

Sign in / Sign up

Export Citation Format

Share Document