scholarly journals CRUDE OIL PRICE FORECASTING BY CEEMDAN BASED HYBRID MODEL OF ARIMA AND KALMAN FILTER

2018 ◽  
Vol 80 (4) ◽  
Author(s):  
Muhammad Aamir ◽  
Ani Shabri ◽  
Muhammad Ishaq
Keyword(s):  
Kalman Filter ◽  
Crude Oil ◽  
Hybrid Model ◽  
Arima Model ◽  
Oil Prices ◽  
Ensemble Empirical Mode Decomposition ◽  
Intrinsic Mode Functions ◽  
Crude Oil Prices ◽  
Mode Decomposition ◽  
Original Time

This paper used complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) based hybrid model for the forecasting of world crude oil prices. For this purpose, the crude oil prices original time series are decomposed into sub small finite series called intrinsic mode functions (IMFs). Then ARIMA model was applied to each extracted IMF to estimate the parameters. Next, using these estimated parameters of each ARIMA model, the Kalman Filter was run for each IMF, so that these extracted IMFs can be predicted more accurately. Finally, all IMFs are combined to get the result. For testing and verification of the proposed method, two crude oil prices were used as a sample i.e. Brent and WTI (West Texas Intermediate) crude oil monthly prices series. The D-statistic values of the proposed model were 93.33% for Brent and 89.29% for WTI which reveals the importance of the CEEMDAN based hybrid model.

scholarly journals A CEEMDAN and XGBOOST-Based Approach to Forecast Crude Oil Prices

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-15 ◽  
Author(s):  
Yingrui Zhou ◽  
Taiyong Li ◽  
Jiayi Shi ◽  
Zijie Qian
Keyword(s):  
Crude Oil ◽  
Global Economy ◽  
Oil Prices ◽  
Ensemble Empirical Mode Decomposition ◽  
Gradient Boosting ◽  
Intrinsic Mode Functions ◽  
Crude Oil Prices ◽  
Novel Approach ◽  
Mode Decomposition ◽  
Extreme Gradient Boosting

Crude oil is one of the most important types of energy for the global economy, and hence it is very attractive to understand the movement of crude oil prices. However, the sequences of crude oil prices usually show some characteristics of nonstationarity and nonlinearity, making it very challenging for accurate forecasting crude oil prices. To cope with this issue, in this paper, we propose a novel approach that integrates complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and extreme gradient boosting (XGBOOST), so-called CEEMDAN-XGBOOST, for forecasting crude oil prices. Firstly, we use CEEMDAN to decompose the nonstationary and nonlinear sequences of crude oil prices into several intrinsic mode functions (IMFs) and one residue. Secondly, XGBOOST is used to predict each IMF and the residue individually. Finally, the corresponding prediction results of each IMF and the residue are aggregated as the final forecasting results. To demonstrate the performance of the proposed approach, we conduct extensive experiments on the West Texas Intermediate (WTI) crude oil prices. The experimental results show that the proposed CEEMDAN-XGBOOST outperforms some state-of-the-art models in terms of several evaluation metrics.

scholarly journals Forecasting Crude Oil Prices Using Ensemble Empirical Mode Decomposition and Sparse Bayesian Learning

Energies ◽  
2018 ◽  
Vol 11 (7) ◽  
pp. 1882 ◽  
Author(s):  
Taiyong Li ◽  
Zhenda Hu ◽  
Yanchi Jia ◽  
Jiang Wu ◽  
Yingrui Zhou
Keyword(s):  
Time Series ◽  
Crude Oil ◽  
Empirical Mode Decomposition ◽  
Bayesian Learning ◽  
Oil Prices ◽  
Ensemble Empirical Mode Decomposition ◽  
Sparse Bayesian Learning ◽  
Crude Oil Prices ◽  
Mode Decomposition ◽  
Model Confidence Set

Crude oil is one of the most important types of energy and its prices have a great impact on the global economy. Therefore, forecasting crude oil prices accurately is an essential task for investors, governments, enterprises and even researchers. However, due to the extreme nonlinearity and nonstationarity of crude oil prices, it is a challenging task for the traditional methodologies of time series forecasting to handle it. To address this issue, in this paper, we propose a novel approach that incorporates ensemble empirical mode decomposition (EEMD), sparse Bayesian learning (SBL), and addition, namely EEMD-SBL-ADD, for forecasting crude oil prices, following the “decomposition and ensemble” framework that is widely used in time series analysis. Specifically, EEMD is first used to decompose the raw crude oil price data into components, including several intrinsic mode functions (IMFs) and one residue. Then, we apply SBL to build an individual forecasting model for each component. Finally, the individual forecasting results are aggregated as the final forecasting price by simple addition. To validate the performance of the proposed EEMD-SBL-ADD, we use the publicly-available West Texas Intermediate (WTI) and Brent crude oil spot prices as experimental data. The experimental results demonstrate that the EEMD-SBL-ADD outperforms some state-of-the-art forecasting methodologies in terms of several evaluation criteria such as the mean absolute percent error (MAPE), the root mean squared error (RMSE), the directional statistic (Dstat), the Diebold–Mariano (DM) test, the model confidence set (MCS) test and running time, indicating that the proposed EEMD-SBL-ADD is promising for forecasting crude oil prices.

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 Improving forecasting accuracy of crude oil prices using decomposition ensemble model with reconstruction of IMFs based on ARIMA model

2018 ◽  
Vol 14 (4) ◽  
pp. 471-483 ◽  
Author(s):  
Muhammad Aamir ◽  
Ani Shabri ◽  
Muhammad Ishaq
Keyword(s):  
Crude Oil ◽  
Moving Average ◽  
Arima Model ◽  
Oil Prices ◽  
Autoregressive Moving Average ◽  
Complex Data ◽  
Ensemble Model ◽  
Intrinsic Mode Functions ◽  
Forecasting Accuracy ◽  
Crude Oil Prices

The accuracy of crude oil price forecasting is more important especially for economic development and is considered a lifeblood of the industry. Hence, in this paper, a decomposition-ensemble model with the reconstruction of intrinsic mode functions (IMFs) is proposed for forecasting the crude oil prices based on the well-known autoregressive moving average (ARIMA) model. Essentially, the reconstruction of IMFs enhanced the forecasting accuracy of the existing decomposition ensemble models. The proposed methodology works in four steps: decomposition of the complex data into several IMFs using EEMD, reconstruction of IMFs based on order of ARIMA model, prediction of every reconstructed IMF, and finally ensemble the prediction of every IMF for the final output. A case study is carried out using two crude oil prices time series (i.e. Brent and West Texas Intermediate (WTI)). The empirical results exhibited that the reconstruction of IMFs based on order of ARIMA model was adequate and provided the best forecast. To check the correctness, robustness and generalizability simulations were also carried out.

scholarly journals Daily Crude Oil Price Forecasting Based on Improved CEEMDAN, SCA, and RVFL: A Case Study in WTI Oil Market

Energies ◽  
2020 ◽  
Vol 13 (7) ◽  
pp. 1852 ◽  
Author(s):  
Jiang Wu ◽  
Feng Miu ◽  
Taiyong Li
Keyword(s):  
Crude Oil ◽  
Critical Role ◽  
Oil Prices ◽  
Ensemble Empirical Mode Decomposition ◽  
Functional Link ◽  
Intrinsic Factors ◽  
Crude Oil Prices ◽  
Target Values ◽  
Predicted Values

Crude oil is one of the strategic energies and plays an increasingly critical role effecting on the world economic development. The fluctuations of crude oil prices are caused by various extrinsic and intrinsic factors and usually demonstrate complex characteristics. Therefore, it is a great challenge for accurately forecasting crude oil prices. In this study, a self-optimizing ensemble learning model incorporating the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), sine cosine algorithm (SCA), and random vector functional link (RVFL) neural network, namely ICEEMDAN-SCA-RVFL, is proposed to forecast crude oil prices. Firstly, we employ ICEEMDAN to decompose the raw series of crude oil prices into a group of relatively simple subseries. Secondly, RVFL is used to forecast the target values for each decomposed subseries individually. Due to the complex parameter settings of ICEEMDAN and RVFL, SCA is introduced to optimize the parameters for ICEEMDAN and RVFL in the above decomposition and prediction stages simultaneously. Finally, we assemble the predicted values of all individual subseries as the final predicted values of crude oil prices. Our proposed ICEEMDAN-SCA-RVFL significantly outperforms the single and ensemble benchmark models, as demonstrated by a case study conducted using the time series of West Texas Intermediate (WTI) daily crude oil spot prices.

scholarly journals A New Approach for Reconstruction of IMFs of Decomposition and Ensemble Model for Forecasting Crude Oil Prices

2020 ◽  
Vol 2020 ◽  
pp. 1-23
Author(s):  
Peng Xu ◽  
Muhammad Aamir ◽  
Ani Shabri ◽  
Muhammad Ishaq ◽  
Adnan Aslam ◽  
...  
Keyword(s):  
Crude Oil ◽  
Moving Average ◽  
Ensemble Empirical Mode Decomposition ◽  
Divide And Conquer ◽  
Computational Time ◽  
Intrinsic Mode Functions ◽  
New Paradigm ◽  
Forecasting Accuracy ◽  
Simple Strategy ◽  
Mode Decomposition

Accurate forecasting for the crude oil price is important for government agencies, investors, and researchers. To cope with this issue, in this paper, a new paradigm is designed for the reconstruction of intrinsic mode functions (IMFs) of decomposition and ensemble models to reduce the complexity in computation and to enhance the forecasting accuracy. Decomposition and ensemble methodologies significantly enhance the forecasting accuracy under the framework of “divide and conquer” with the proposed reconstruction of IMFs method. The proposed approach used the autocorrelation at lag 1 of all IMFs for the reconstruction. The ensemble empirical mode decomposition (EEMD) technique is employed to decompose the data into different IMFs. Models that utilized the decomposed data relatively perform well, as compared to its application to the undecomposed data. However, sometimes, the decomposition may produce poor results due to the error accumulation at the end. Thus, in this study, the reconstruction of IMFs is proposed for minimizing the aforementioned error, thereby increasing the forecasting accuracy. The Brent and West Texas Intermediate (WTI) datasets (daily and weekly) are exploited to compare the forecasting performance of autoregressive integrated moving average (ARIMA) along with artificial neural network (ANN) models with the decomposed data. The results have proven that the new paradigm of reconstruction of IMFs through autocorrelation was a better and simple strategy that significantly improved the performance of single models including ARIMA and ANN. Hence, it is concluded that the proposed model takes less computational time and achieved higher forecasting accuracy with the reconstruction of IMFs as opposed to using all IMFs.

scholarly journals Pemilahan Volatilitas Harga Daging Sapi Menggunakan Metode Ensemble Empirical Mode Decomposition

2020 ◽  
Vol 38 (1) ◽  
pp. 41
Author(s):  
Fitria Hasanah ◽  
Hari Wijayanto ◽  
I Made Sumertajaya
Keyword(s):  
Empirical Mode Decomposition ◽  
Arima Model ◽  
Price Volatility ◽  
Ensemble Empirical Mode Decomposition ◽  
Food Prices ◽  
Intrinsic Mode Functions ◽  
Import Quota ◽  
Mode Decomposition ◽  
The Government ◽  
Beef Prices

<strong>English</strong><br />Staple food prices include the major determinants of households food security and general inflation. Beef is a basic food which its price is controlled by the Government of Indonesia. This study aims to identify the determinants beef price volatility using the Ensemble Empirical Mode Decomposition (EEMD) method. The data was a weekly series of Januari 2006–Desember 2018 obtained from the Ministry of Trade. EEMD extracts data into a number of Intrinsic Mode Functions (IMFs) that are independent which are then used to forecast beef prices with the ARIMA model. EEMD produced 6 IMFs and one residual. The residual contributed 99.85% to beef price volatility. This means that the long-term trend of beef prices is determined by the residual trends. The EEMD results indicate that the high beef price volatility in certain periods is mainly due to high demand during the Ramadhan month and Idul Fitri, import quota policy, and changes in exchange rates and petroleum prices. The IMF and residual based ARIMA forecasting model obtained MAPE value of 0.42% but with contradicting directions. The Government may use the import quota as a policy instrument for stabilizing the beef price.<br /><br /><br /><strong>Indonesian</strong><br />Harga pangan pokok termasuk faktor penentu utama ketahanan pangan rumah tangga dan inflasi umum. Daging sapi adalah salah satu bahan pangan pokok yang harganya dikendalikan Pemerintah Indonesia. Penelitian ini bertujuan mengidentifikasi faktor penentu volatilitas harga daging sapi dengan metode <em>Ensemble Empirical Mode Decomposition</em> (EEMD). EEMD menguraikan data menjadi sejumlah <em>Intrinsic Mode Function</em> (IMF) yang saling bebas yang selanjutnya digunakan untuk melakukan peramalan harga daging sapi dengan model ARIMA. Data yang digunakan adalah harga daging sapi mingguan Januari 2006–Desember 2018 yang diperoleh dari Kementerian Perdagangan. EEMD menghasilkan 6 IMF dan satu sisaan. Sisaan IMF memberikan kontribusi sebesar 99,85% terhadap pergerakan harga daging sapi. Artinya bahwa tren jangka panjang harga daging sapi ditentukan oleh tren sisaan. Berdasarkan hasil EEMD, volatilitas harga daging sapi yang tinggi pada periode-periode tertentu dipengaruhi oleh beberapa faktor terutama tingginya permintaan selama bulan Ramadhan dan Idul Fitri dan kebijakan kuota impor, serta perubahan nilai tukar rupiah dan harga BBM. Model peramalan ARIMA yang diduga berdasarkan IMF dan sisaan IMF menghasilkan nilai MAPE sebesar 0,42%, namun arah perubahannya tidak bersesuaian. Disarankan agar pemerintah menggunakan kuota impor sebagai salah satu instrumen kebijakan stabilisasi harga daging sapi.

scholarly journals Forecasting Daily Crude Oil Prices Using Improved CEEMDAN and Ridge Regression-Based Predictors

Energies ◽  
2019 ◽  
Vol 12 (19) ◽  
pp. 3603 ◽  
Author(s):  
Taiyong Li ◽  
Yingrui Zhou ◽  
Xinsheng Li ◽  
Jiang Wu ◽  
Ting He
Keyword(s):  
Crude Oil ◽  
Ridge Regression ◽  
Global Economy ◽  
Evaluation Criteria ◽  
Oil Prices ◽  
Ensemble Empirical Mode Decomposition ◽  
Oil Price ◽  
Price Forecasting ◽  
Crude Oil Price ◽  
Crude Oil Prices

As one of the leading types of energy, crude oil plays a crucial role in the global economy. Understanding the movement of crude oil prices is very attractive for producers, consumers and even researchers. However, due to its complex features of nonlinearity and nonstationarity, it is a very challenging task to accurately forecasting crude oil prices. Inspired by the well-known framework “decomposition and ensemble” in signal processing and/or time series forecasting, we propose a new approach that integrates the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), differential evolution (DE) and several types of ridge regression (RR), namely, ICEEMDAN-DE-RR, for more accurate crude oil price forecasting in this paper. The proposed approach consists of three steps. First, we use the ICEEMDAN to decompose the complex daily crude oil price series into several relatively simple components. Second, ridge regression or kernel ridge regression is employed to forecast each decomposed component. To enhance the accuracy of ridge regression, DE is used to jointly optimize the regularization item, the weights and parameters of each single kernel for each component. Finally, the predicted results of all components are aggregated as the final predicted results. The publicly available West Texas Intermediate (WTI) daily crude oil spot prices are used to validate the performance of the proposed approach. The experimental results indicate that the proposed approach can achieve better performance than some state-of-the-art approaches in terms of several evaluation criteria, demonstrating that the proposed ICEEMDAN-DE-RR is very promising for daily crude oil price forecasting.

Sign in / Sign up

Export Citation Format

Share Document