Crude oil price prediction method and system based on CEEMD-PSO-BP model and error compensation

Abstract

The present invention provides a crude oil price prediction method and system based on the CEEMD-PSO-BP model and error compensation, comprising the following steps: using CEEMD to decompose the non-stationary crude oil price sequence into a series of IMF components and trend components with different frequency characteristics ;Use the PSO-BP model to predict each IMF component and trend component respectively, obtain the predicted value of each component and obtain the initial forecast sequence by linearly superimposing it; use the original crude oil price sequence to subtract the initial forecast sequence to obtain the error sequence; use CEEMD decomposes the error sequence into a series of imf components and trend components with different frequency characteristics, and uses the PSO-BP model to predict each imf component and trend component separately, obtains the predicted value of each component, and obtains the error prediction by linearly superimposing them sequence; finally, the initial forecast sequence and the error prediction sequence are linearly superimposed to obtain the final crude oil price prediction sequence. This method reduces the difficulty of crude oil price prediction and has higher accuracy.

Description

technical field [0001] The invention relates to the field of crude oil price forecasting, in particular to a crude oil price forecasting method and system based on the CEEMD-PSO-BP model and error compensation. Background technique [0002] International crude oil prices are not only closely related to the international economic situation, but also inseparable from my country's economic development. Fluctuations in international oil prices will have a huge impact on my country's economic development, and bring many uncertainties to the Chinese government and related business organizations, causing turmoil in the domestic oil market. This is not only detrimental to the development of my country's macro economy, but also causes instability in the middle and lower reaches of the oil industry chain and the loss of foreign exchange reserves. Therefore, accurate forecasting of crude oil prices has important guiding significance for maintaining my country's economic stability and h...

AI Technical Summary

Problems solved by technology

Due to the highly non-stationary, nonlinear and random characteristics of crude oil price time series data, it is difficult to obtain accurate prediction results for the original crude oil price time series prediction method

At present, most of the crude oil price time series prediction methods that incorporate data decomposition technology use a single data decomposition technology to decompose the crude oil price time series data to reduce the non-stationarity of the data series. This method improves the prediction accuracy to a certain extent, but Since there are still high-frequency oscillating data sequences in the decomposed data sequences, it is difficult to greatly improve the prediction accuracy

Images