基于ARIMA与神经网络集成的GDP时间序列预测研究

本文深入分析了单整自回归移动平均(ARIMA)模型与神经网络(NN)模型的预测特性和优劣,并在此基础上建立了由ARIMA模型和NN模型集成的GDP时间序列预测模型与算法。其基本思想是充分发挥两种模型在线性空间和非线性空间的预测优势,据此将GDP时间序列的数据结构分解为线性自相关主体和非线性残差两部分,首先用ARIMA模型预测序列的线性主体,然后用NN模型对其非线性残差进行估计,最终集成为整个序列的预测结果。仿真实验表明:集成模型的预测准确率显著高于单一模型的预测准确率,从而证实了集成模型用于GDP预测的有效性。

Research on GDP Time Series Forecasting Based on Integrating ARIMA with Neural Networks

Based on analysis of the autoregressive integrated moving average(ARIMA) and neural networks (NN) models,this paper presents an ensemble approach to GDP time series forecasting which integrating ARIMA with NN.The GDP time series are considered to be composed of a linear autocorrelation structure and nonlinear structure.ARIMA is used to model the linear component of GDP time series and the NN model is applied to the nonlinear residuals component prediction.The results of GDP forecasting show that the propose...