A multiple adaptive wavelet recurrent neural network model to analyze crude oil prices

International crude oil prices are an important part of the economy, and trends in changing oil prices have an effect on financial markets. Traditional hybrid analysis methods for international crude oil prices, such as wavelet transform and back propagation neural network (BPNN), seek synergy effects by sequentially filtering data through different models. However, these estimation methods cause loss of information through the introduction of biases in each filtering step, which are aggregated throughout the process when model assumptions are violated, and the traditional BPNN model does not have forecasting ability. In this study, we constructed a multiple wavelet recurrent neural network (MWRNN) simulation model, in which trend and random components of crude oil and gold prices were considered. The wavelet analysis was utilized to capture multiscale data characteristics, while a real neural network (RNN) was utilized to forecast crude oil prices at different scales. Finally, a standard BPNN was added to combine these independent forecasts from different scales into an optimal prediction of crude oil prices. The simulation results showed that the model has high prediction accuracy. The designed neural network is able to predict oil prices with an average error of 4.06% for testing and 3.88% for training data. This forecasting model would be able to predict the world crude oil prices with any commercial energy source prices instead of the gold prices.

► Our study develop one multiple wavelet recurrent neural network (MW-RNN) model for analyzing and forecasting international crude oil prices series.
► we combine the dynamic properties of recurrent neural network (RNN) and wavelet decomposition together in MW-RNN model.
► MR-RNN is able to predict the oil prices with an average error of 4.06% for testing and 3.88% for training data.