Research on material demand analysis of manufacturing industry based on time series model—ARIMA

Abstract

In order to solve the problem of mismatch between material production plan and actual demand, this paper analyzes and forecasts the material demand of manufacturing industry. Firstly, the material demand frequency at different time points in the historical production data of a manufacturing industry is calculated by statistical method. Secondly, it quantitatively analyzes the change trend of the total sales volume of each material at different time points to the unit price of the material. Thirdly, with the quantity, frequency, total sales and unit price of materials as characteristic factors, through relevant statistical analysis, six kinds of materials are synthesized. Finally, according to the demand data of these six materials, the time characteristics are transformed into weekly characteristics, and the time series model ARIMA is applied to construct the weekly prediction model of material demand, and the performance of the prediction model is evaluated. The results show that the comparison between the forecast results and the actual values of the weekly forecast model passes the test and has a good application prospect.