Open AccessSingle Exponential Smoothing Method to Predict Sales Multiple Products
Author(s) -
Rendra Gustriansyah
Publication year - 2018
Publication title -
insist (international series on integrated science and technology)
Language(s) - English
Resource type - Journals
ISSN - 2502-8588
DOI - 10.23960/ins.v3i2.176
Subject(s) - exponential smoothing , mean absolute percentage error , smoothing , stock (firearms) , econometrics , statistics , value (mathematics) , exponential function , moving average , computer science , mathematics , mean squared error , engineering , mechanical engineering , mathematical analysis
—Activity to predict sales multiple products intended for control of the number of existing stock, so the lack or excess stock can be minimized. When the number of sales can be accurately predicted, then the fulfilment of consumer demand can be cultivated in a timely and cooperation with suppliers maintained properly so that company can avoid losing sales and customers. This study aims to predict sales multiple products (6,877 products) using Single Exponential Smoothing (SES) approach, which is expected to improve the efficiency of the inventory system. Measurement accuracy of prediction in this study using a standard measurement Mean Absolute Percentage Error (MAPE), which is the most important criteria in analyzing the accuracy of the prediction. The results showed that the average of percentage prediction error of products using SES is high, because MAPE value obtained is 1.056% with a smoothing parameter α = 0.9