<![CDATA[Aluminum is one of the most important metals for the industrial world, but currently, aluminum is scarce due to a shortage of electricity, which makes manufacturers limit their production. Therefore, to overcome this scarcity, the government imports aluminum. Imports that are carried out continuously will more or less affect the wheels of the economy in this country. Therefore, it is necessary to predict the value of aluminum imports in the future so that later the demand for aluminum in Indonesia is stable and not too excessive in importing. The prediction method used is the Powell-Beale algorithm, which is one of the most commonly used artificial neural network methods for data prediction. This paper does not discuss the prediction results. Still, it discusses the ability of the Powell-Beale algorithm to make predictions based on imported Aluminum datasets obtained from the Central Statistics Agency. The research data used is aluminum import data by the leading country of origin from 2013-to 2020. A network architecture model will be formed and determined based on this data, including 3-15-1, 3-20-1, and 3-25-1. From these five models, after training and testing, the results show that the best architectural model is 3-20-1 with an MSE value of 0,03010927, the lowest among the other four models. So it can be concluded that the model can be used to predict aluminum imports.]]>
Copyrights © 2022
