SARIMA – A Model for Forecasting Product order demand

Abstract

Abstract: Product analysis is the most important part for any working manufacturing. It provides the sales record of their currently manufactured product and also it helps to predict its performance in the future. For this analysis, a SARIMAX model has been used with Time series forecasting. This paper will explain the need of such model instead of using a simple regression model to predict the order demand. This study analyses and presents a forecasting model to predict an order demand for the Product over the time period. Demand in Product is a main component for planning all processes in supply chain, and therefore determining Product demand is a great interest for supply chain. Mean forecasting for product order demand was carried out using SARIMA model, by using the past data from the period of 2011 to 2017. The model with the least value of Akaike Information Criterion (AIC) was selected as the appropriate model for forecasting mean Error. Test for normality of residuals were performed to see the adequacy of the chosen model. SARIMA (1, 1, 1) (0, 1, 1) (12) was selected as the best model for mean product order demand forecast. The results obtained will prove that the model could be utilized to forecast the future demand in the Product manufacturing industry. These results will help the manufacturers for manufacturing reliable guidelines in making decisions. Keywords: ARIMA, AIC, S-ARIMA, Regression