Energy futures prices forecasting by novel DPFWR neural network and DS-CID evaluation

摘要: Abstract In recent years, artificial neural networks have been employed a lot in forecasting financial price series. Crude oil and natural gas play the most important role energy markets. Besides, crude fluctuations are closely linked to A novel hybrid network, DPFWR is put forward this paper. The proposed combines double parallel feedforward network wavelet analysis theory with random time effective function. We apply forecast futures series, including WTI oil, Brent gas, RBOB gasoline, heating Rotterdam coal. order compare accuracy of results, several error criteria applied evaluate errors BP, DPF, LSTM, SARIMA models. new method for evaluation, called DS-CID, developed an attempt observe superiority network. Based on empirical analysis, performance can be distinguished from other models by its great research.