基于灰色多元线性回归组合模型的中国社会消费品零售总额影响因素及预测研究

Research on Influencing Factors and Forecast of Total Retail Sales of Consumer Goods in China based on Grey Multivariate Linear Regression Combination Model

影响中国社会消费品零售总额因素众多,但研究社会消费品零售总额组合模型尚属空白领域。通过Shapley值法构建灰色多元线性回归组合模型改善了原有灰色模型中没有考虑线性因素和线性回归模型中没有考虑指数增长趋势的缺陷,同时能公平反应组合中各种方法对组合的平均贡献及重要性。灰色多元线性回归组合模型对社会消费品零售总额预测结果显示,在保持现状的基础上,在未来的一定时期内,社会消费品零售总额将继续保持稳速增长趋势。

There are many factors that affect the total retail sales of consumer goods in China,but there are still blank areas to study the combination model of total retail sales of social consumer goods. The Shapley value method was used to construct the combination model of grey multivariate linear regression,which improves the defect that the original grey model does not consider the linear factors and the linear regression model does not consider the exponential growth trend. At the same time,it can fairly reflect the average contribution and importance of various methods in combination. The prediction results of the gray multiple linear regression combination model on the total retail sales of social consumer goods show that,on the basis of maintaining the status quo,the total retail sales of social consumer goods will continue to maintain a steady growth trend for a certain period in the future.