Prediction of the National Total Retail Sales of Consumer Goods Based on ARIMA Model

Abstract

This article selects the data of Chinese Total Retail Sales of Consumer Goods from 1952 to 2016 and then established ARIMA (2,1,2) model after the comparative test. It is found that the relative error between actual numbers and predictive numbers from 2011 to 2016 is smaller than 3%. Therefore, it is feasible to use the ARIMA (2,1,2) model to predict the short-term data of Chinese Total Retail Sales of Consumer Goods. The prediction is that consumer markets will increase by more than 10% with little volatility.