Implementation of Artificial Neural Network for Product Sales Prediction at Rice Milling Unit (RMU)
Mendarissan Aritonang (a*) Denny Jean Cross Sihombing (b)
a) Informatics Management Department
Methodist University of Indonesia Medan, Indonesia.
b) Information System Department Atma Jaya Catholic University of Indonesia Jakarta, Indonesia.
Abstract
In North Sumatra, there are many rice fields and rice milling factories (Rice Milling Units). Rice Milling Units (RMU) are still many who have not applied the prediction method for the sale of rice so that it can affect the availability of raw materials. The purpose of this research is forecasting product sales (rice) at RMU so that it can know the number of raw materials needed so that will avoid idle time. To obtain optimal forecasting, it will be compared 2 (two) forecasting method, Linear Regression and Artificial Neural network with Backpropagation algorithm. The results showed the value of MSE on linear regression method of 214, while at the time using Artificial Neural Network obtained MSE value of 0.00099713. Based on the value of the MSE, it is seen that the smallest MSE is forecasting by Artificial Neural Network method. The results of forecasting sales of rice starting from June 2019 to May 2020 (in tonnes) are 98, 82, 85, 85,123, 91, 95, 98, 84, 124, 101, 75 Keywords— Artificial Neural Network, Sales Forecasting, Backpropagation, Linear Regression
Keywords: Artificial Neural Network, Sales Forecasting, Backpropagation, Linear Regression
Topic: Computer and Communication Engineering