PERBANDINGAN METODE ANN BACKPROPAGATION DAN ARMA UNTUK PERAMALAN INFLASI DI INDONESIA

Abstract

A country's development progress can be measured by good economic growth. If economic growth experiences rapid growth, it will usually trigger price increases. The occurrence of an uncontrolled increase in the price of goods or services for the needs of the community can cause inflation. inflation rate for a country is an inflation rate that has a low and stable value. One alternative is to provide an overview of the inflation in Indonesia by using forecasting analysis techniques. In this study, inflation forecasting analysis in Indonesia was carried out using the ANN Backpropagation and ARMA methods. The purpose of this research is to compare the performance results of the two methods and look at the best method for forecasting results. Based on the results of the analysis with the ANN Backpropagation method, the best network architecture model was ANN(7-4-1) using an epoch value of 400 and a learning rate of 0,1 with a value of MSE = 0,0112 and RMSE = 0,1065. While the results of the analysis using the ARMA method, the best model was obtained, namely ARMA(2,0,1) with the value MSE = 0,0648 and RMSE = 0,2545. So that the most optimal method used to predict inflation for the next period is the ANN Backpropagation method because it has a smaller error value. From this model, the results of forecasting inflation rates for the months of May to December 2022 are also obtained with a range of 0,01% to 0,5%.