基于灰度统计和神经网络的物流业税收预测模型

Taxation Forecasting Model of Logistics Industry Based on Grey Statistics and Neural Network

针对物流业税收相关数据的高相关性和冗余等问题,提出一种基于改进灰度统计和神经网络的物流业税收预测模型,预测模型应用灰度统计方法解决原始数据的相关性和冗余问题,应用最优化的神经网络确定预测模型的参数,以提高预测模型的准确性。以中国国家年鉴和某省年鉴为数据来源对预测模型进行检验,结果表明,基于灰度统计和神经网络原理建立的预测模型能够快速优化参数并提供更准确的预测结果,模型的自学习能力适用于税收预测等,具有较高的实用价值。

In this paper, in view of the problems of the data concerning the taxation of the logistics industry, we proposed a taxation forecasting model for the industry based on improved grey statistics and neural network and then tested the model with the Chinese Yearbook and the yearbook of a certain province as the data source, which demonstrated the accuracy of the model.