Analysis and Forecasting of Nonlinearity in Oil Market

This research aims to introduce an ideal model for forecasting Iranian crude oil price movements. It tries to make an all-out analysis of this energy product. Therefore, we tested the ‘predictability’ hypothesis by using the variance ratio test, BDS test and the chaos series test. Later, a structural analysis is a carried out to investigate possible nonlinear patterns in the series. Lyapunov exponents confirmed that the return series of crude oil prices were chaotic. Moreover, According to our findings, the return series has the long memory property which, rejecting efficient markets hypothesis, affirms the fractal market hypothesis. The GPH test verifies that both return and volatility series of crude oil price have the long-memory property. Besides, according to both MSE and RMSE criteria, wavelet-decomposed data significantly improves the performance of model. As a result, we introduce a hybrid model based on the long-memory property which uses wavelet decomposed data as the most accurate model.