Hybrid of Cuckoo Search Algorithm with Lévy Flight and Neural Network for Crude Oil Prices Prediction

Abstract

Accurate prediction of crude oil price can successfully be used to deviate from the negative impact of the crude oil price hike. Limitations of previous studies prompt the proposal of an alternative approach for the hybridization of Cuckoo Search Algorithm with lévy flight and Back-propagation neural network (CSBP) for the estimation of crude oil price to enhance convergence speed accuracy. To evaluate the effectiveness of the proposed CSBP, we used ABC to train BP neural network (ABCNN) and Levenberg-Marquardt neural network (ABCLM) to develop an approach for crude oil price prediction. The outcomes of simulated comparative indicate that the proposed CSBP outperforms the ABCLM and ABCNN in both accuracy and convergence speed. Analysis of variance including post hoc multiple comparative test shows that the performance of the proposed CSBP is statistically significant than the comparison algorithms. The negative side of the crude oil prices in the global market can be defeated with proper planning based on the crude oil prices predicted by the CSBP. The CSBP proposed in this paper could provide a new strategy for risk managers and analysts to create an efficient risk management framework to formulate policies related to risk issues in the global crude oil market.