基于时间序列模型和BP神经网络的山东省GDP预测分析
GDP Forecast Analysis of Shandong Province Based on Time Series Model and BP Neural Network

GDP是衡量国家经济水平的重要指标，准确预测显得尤为重要。本文主要选择1978年至2021年的山东省GDP数据，其中将1978年至2018年的数据作为训练集用于构建模型，2019年至2021年GDP数据作为测试集用于检验模型的准确度，文章运用ARIMA对山东省GDP建立时间序列模型，同时采取BP神经网络对GDP数据进行预测。根据模型预测的结果与实际数据对比，确定最优时间序列模型ARIMA (1, 3, 2)，并对山东省2022年的GDP数值进行预测，为山东省经济发展提供借鉴和参考。
GDP is an important indicator to measure the level of national economy, and it is particularly im-portant to forecast it accurately. This paper mainly selects the GDP data of Shandong Province from 1978 to 2021, in which the data from 1978 to 2018 are used as the training set to build the model, and the GDP data from 2019 to 2021 are used as the test set to test the accuracy of the model. In this paper, ARIMA is used to establish a time series model of GDP in Shandong Province, and BP neural network is used to predict the GDP data. According to the comparison between the predicted results of the model and the actual data, the optimal time series model ARIMA (1, 3, 2) is deter-mined, and the GDP value of Shandong Province in 2022 is predicted to provide reference for the economic development of Shandong Province.