OPEC crude oil prices prediction based on chaos theory and GMDH-GA Algorithm

The price of crude oil is exposed to various factors that cause random, sudden and chaotic price fluctuations. Accurate forecasting of oil prices has a central impact on the macro economy. The aim of this study is to predict the fluctuations of OPEC crude oil in the long-term using chaos theory and GMDH-GA algorithm. First, the daily oil price time series is decomposed by wavelet transformation. Then, chaos is tested using embedding dimension, Lyapunov power and GA tests. Finally, time series noises are reduced by reconstructing the wavelet phase space. Three nonlinear models, GMDH-GA model, GMDH-GA wavelet model, and GMDH-GA extended model, were used to forecast time series. Although the results showed that all three models are favorable in terms of root mean square error (RMSE) and correlation coefficient, but the developed GMDH-GA neural network model with low RMSE and high correlation coefficient is the most effective in predicting the daily price of OPEC crude oil. has it.

کلیدواژه ها:

OPEC crude oil price forecast ، GMDH-GA ، Chaos Theory ، Renyi dimension ، Correlation Dimension