Abstract

The method of time series suitable for use when it checks each data patterns systematically and has many variables, such as in the case of crude oil prices. One study that utilizes the methods of time series is the integration between Ensemble Empirical Mode Decomposition (EEMD) and neural network algorithms based on Polak-Ribiere Conjugate Gradient (PCG). Type of neural network using Feedforward Neural Network (FNN). However, FNN requires setting free parameters in the learning process. Meanwhile, the appropriate parameters are needed to get accurate forecasting results. This research proposes the integration between EEMD and Generalized Regression Neural Network (GRNN). GRNN has advantages, such as: does not require any parameter settings and a quick learning process. For the evaluation, the performance of the method EEMDGRNN compared with GRNN. The experimental results showed that the method EEMD-GRNN produce better forecasting of GRNN. Method of EEMD-GRNN has a value of MSE and RMSE smaller than GRNN. The value of MSE and RMSE used test data for WTI successively equal 0.0032 and 0.0569. While the value of MSE and RMSE used test data for Brent successively equal 0,0017 and 0,0415.

Authors and Affiliations