INFLATION FORECASTS IN AMBON USING NEURAL NETWORK APPLICATIONS BACKPROPAGATION

An artificial Neural Network is the processing of information systems on certain characteristics which are artificial representations based on human neural networks. Artificial Neural Networks can be applied to various fields in human life, one of which is the economic field. In this study, the Artificial Neural Network is used to predict the inflation rate using the Backpropagation method. The data used in this study is 144 data, with 100 data as training data and 44 data as test data taken from the Central Statistics Agency of Maluku Province from 2008-2019. The best prediction accuracy level is obtained by using learning rate (a) = 0.1, Target Error = 0.000001, Maximum epoch = 500, network architecture 11-1, and 70% training data sharing scheme and 30% test data. The average absolute error percentage (MAPE) is 85.21%.