Prediksi stok barang di PT. Satria Jaya Prima menggunakan algoritma SES

A problem requires a solution to solve it. One of them is by using Prediction.
PT. Satria Jaya Prima, when going to order goods to the center does not have
definite information about the stock of goods available in the warehouse. Therefore,
we need a tool in the form of software that can help facilitate and maximize the
performance of company employees in predicting the number of items that must be
ordered to the center for the following month. The data used in this research is
historical data in the form of Dynamix Cement, Semen Padang, Power Max
Cement, Tecking Tires and Fosroc Waterproof Paint in the last 100 months. Single
Exponential Smoothing is a method that continuously improves forecasting by
taking the past average value of smoothing (smoothing) from a time series data in
a decreasing way (exponential). In this study, an evaluation of the prediction results
with MAPE (mean absolute percentage error) will be carried out. The smallest
error value or the one with the lowest error is obtained when using the Single
Exponential Smoothing (SES) method with an alpha value of 0.1-0.9, the difference
between the alpha values used is influenced by the different amounts of each item.
The programming language used is the PHP programming language, using MySQL
in processing the database. The results of this study were obtained on Semen
Padang with an alpha of 0.2-0.3 with an MAPE value of 15%, Semen Power Max
with an alpha of 0.7-0 .9 MAPE 22%, Semen Dynamix with an alpha of 0.8-0.9 with
a MAPE value of 21%, Tecking Tires with an alpha of 0.5-0.9 MAPE values of 24%
and Fosroc Waterproof Paint with an alpha of 0.8-0.9 MAPE values of 24%.

Keywords: Stock prediction, Single Exponential Smoothing (SES), PHP, MySQL