基于灰色BP神经网络的我国工业增加值预测研究

针对我国工业增加值存在季节波动性等外部因素影响其预测准确性不高的问题，提出了一种基于灰色BP神经网络的工业增加值预测算法，即采用以我国2008~2017年各季度工业增加值数据作为时间序列建立的灰色BP神经网络预测模型进行预测。结果表明，采用灰色BP神经网络组合模型预测的精度较灰色模型和BP神经网络模型精度分别提升了0.94%~4.98%和0.01%~0.08%，稳定性分别提升了1.43%~2.97%和0.03%~0.05%。此实验结果验证了灰色BP神经网络组合模型可以有效预测我国工业增加值的发展趋势，进而为政府部门制定工业发展政策提供有效依据。

Research on Forecast of China's Industrial Added Value Based on Gray BP Neural Network

Aiming at the problem that China''s industrial added value is affected by external factors such as seasonal volatility, thus leading to its low forecast accuracy, an industrial added value forecasting model based on gray BP neural network was proposed. The model was established by taking the industrial value-added data of each quarter in China from 2008 to 2017 as the time series. It is a combined one. The results showed that the prediction accuracy of the combination model of gray BP neural network was improved by 0.94%~4.98% and 0.01%~0.08% ccompared with the gray model and BP neural network model, respectively, and the stability was improved by 1.43%~2.97% and 0.03%~0.05 compared with the gray model and the BP neural network model,restictively. The experimental results verified that the gray BP neural network combination model can effectively predict the development trend of the industrial added value, and provided an effective basis for government departments to formulate industrial development policies.