Integrating Wavelet Decomposition and Fuzzy Transformation for Improving the Accuracy of Forecasting Crude Oil Price

Abstract

In this paper, hybrid methods are proposed to predict OPEC crude oil. In the preprocessing step, the wavelet decomposition has been used to reduce the noise of time series, which divides the original data into five levels. Also, the fuzzy transform (F-transform) is applied for its potency of management uncertainty due to the fluctuation of data. F-transform is for decomposing the time series data and afterward, this decomposed data are employed on the ground of inputs. Because of the nonlinearity of the time series structure, integrating the mentioned proposed algorithms with the multilayer perceptron (MLP), radial basis functions, group method of data handling (GMDH), adaptive neuro-fuzzy inference system (ANFIS), and support vector regression (SVR) are applied for prediction of time series relevant to the crude oil price. By comparing the results of models, L5-ANFIS, L5-MLP, L5-GMDH, L5-SVR are more appropriate than others for predicting OPEC crude oil price.

Managing Economic Uncertainty: Fuzzy Computational Models in International Oil Economy Forecasting

“…The introduction of hybrid methods through Saghi, F. et al [20] makes it easier to predict OPEC crude oil prices. To handle uncertainty, the pre-processing stage employs the fuzzy transform (F-transform), and wavelet decomposition is utilized to lower time series noise.…”

“…To handle uncertainty, the pre-processing stage employs the fuzzy transform (F-transform), and wavelet decomposition is utilized to lower time series noise. Adaptive neuro-fuzzy inference system (ANFIS), support vector regression (SVR), radial basis functions (RBFs), group method of data handling (GMDH) [20], and multilayer perceptrons (MLPs) are some of the techniques that incorporate these methodologies. Among the models tested, L5-ANFIS, L5-MLP, L5-GMDH, and L5-SVR performed the best when it came to forecasting the price of OPEC crude oil [21].…”