基于灰色关联和BP神经网络的汽车保有量预测

为提高汽车保有量的预测准确性,运用灰色关联分析法,计算分析与汽车保有量相关的主要社会指标,确定汽车保有量的影响因子分别为国民总收入、人均GDP、进出口总额、城镇居民人均可支配收入、钢材产量、公路客运量和社会消费品零售总额。将所确定的因子作为汽车保有量的预测指标,建立基于BP神经网络的汽车保有量预测模型,并对模型进行应用测试。结果表明:BP神经网络模型具有较高的精度,最大相对误差为2.2%,平均相对误差为1.5%。,可为我国汽车保有量的预测研究提供方法支撑。

Prediction of Car Ownership Based on Grey Relational Analysis and BP Neural Network

In order to improve the forecast ability of car ownership,by using gray correlation method,this paper analyzed the main factors related to car ownership,which are gross national income, per capita GDP, gross import and export, urban resident disposable income, steel output, highway passenger transport volume, total retail sales of consumer goods. The prediction model of car ownership was established based on BP neural network, and then verified with tests. The results show that car ownership can be predicted accurately by the model based on BP neural network. The maximum relative error is 2.2% and the average relative error is 1.5%.In addition, this predictive model provided a method for car ownership.