Autoregressive Integrated Moving Average (ARIMA) Model of Forecast Demand in Distribution Centre

Abstract

Demand forecasting is very important to be done in order to meet the demand for nail products that are available in every DC. This article tries to present the basic method of time series analysis and forecasting performance of Autoregressive Integrated Moving Average (ARIMA) Model. The study uses this ARIMA model because this model can include the variables used and the type of time series data. Calculation of forecasting errors to be used is Mean Square Error (MSE). From the results of data processing analysis, the best ARIMA model for DC Aceh demand forecasting is ARIMA (3,0,2) with 63,578 units of nails, DC Padang is ARIMA (3.0,3) with a forecasting result of 59,853 units of nails, DC Pekanbaru is ARIMA (1,0,2) with forecasting results of 53,043 units of nails, DC Palembang is ARIMA (3.0,1) with forecasting results of 57,682 units of nails, and DC Medan is ARIMA (2.0,1) with results forecasting 63,699 units of nails.