Nadia Roosmalita Sari, Wayan Firdaus Mahmudy, Aji Prasetya Wibawa
Inflation is the increase of prices of goods that can affect other prices of goods. Inflation is a main economic problem often faced by society. This economic problem could cause detrimental economic, political, and social effects. Inflation can be caused by a variety of sources. One of them comes from imported goods. Therefore, forecasting is needed to find out the inflation rate in the future. Inflation forecasting can be used to prepare government policies to keep inflation at a low level. In addition, the forecasting results can also be utilized by all members of the society. This study proposed the Backpropagation Neural Network method to forecast the inflation rate in the future. This study used time-series data of inflation rate and CPI (Consumer Price Index). The tested data resulted in a forecast. The RMSE (Root Mean Square Error) technique was used to test the accuracy of the forecasting results. This study also implemented the Sugeno FIS model as a comparison method. The result showed that the performance of the proposed method is better than the comparison method with an RMSE value of 0.204.
Faculty of Computer Science, Universitas Brawijaya, Jln Veteran, Malang, East Java, 65145, Indonesia; Faculty of Engineering, Universitas Negeri Malang, Jln Semarang, Malang, East Java, 65145, Indonesia
