A comparison study between time series model and ARIMA model for sales forecasting of distributor in plastic industry

Abstract

The number of distributors in plastic industry is increasing every year. Therefore, they got a problem about competitive cost more than in the past. One of the ways to solve this problem is management by inventory. Before they improve inventory, the forecasting is important for this process. In the past, they were looking for conventional time series for forecasting sales volume before manages inventory. This study would like to compare the application of three forecasting methods on the amount of the sales volume for plastic distributor, the ARIMA time series method,Moving average method and Holt's and Winter exponential method. After applying five data sets of raw material from plastic distributor by four forecasting methods, the ARIMA model shows better results than other models when compare with other methods by using MAPE (Mean Absolute Percentage Error).