文章基本信息

标题：Backpropagation on Neural Network Method For Inflation Rate Forecasting in Indonesia
本地全文：下载
作者：Nadia Roosmalita Sari ; Wayan Firdaus Mahmudy
期刊名称：International Journal of Advances in Soft Computing and Its Applications
印刷版ISSN：2074-8523
出版年度：2016
卷号：8
期号：3
出版社：International Center for Scientific Research and Studies
摘要：Inflation is the increase of prices of goods that can affect otherprices of goods. Inflation is a main economic problem often faced bysociety. This economic problem could cause detrimental economic,political, and social effects. Inflation can be caused by a variety ofsources. 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 tokeep inflation at a low level. In addition, the forecasting results canalso be utilized by all members of the society. This study proposedthe Backpropagation Neural Network method to forecast theinflation rate in the future. This study used time-series data ofinflation rate and CPI (Consumer Price Index). The tested dataresulted 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 comparisonmethod. The result showed that the performance of the proposedmethod is better than the comparison method with an RMSE valueof 0.204Inflation is the increase of prices of goods that can affect otherprices of goods. Inflation is a main economic problem often faced bysociety. This economic problem could cause detrimental economic,political, and social effects. Inflation can be caused by a variety ofsources. 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 tokeep inflation at a low level. In addition, the forecasting results canalso be utilized by all members of the society. This study proposedthe Backpropagation Neural Network method to forecast theinflation rate in the future. This study used time-series data ofinflation rate and CPI (Consumer Price Index). The tested dataresulted 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 comparisonmethod. The result showed that the performance of the proposedmethod is better than the comparison method with an RMSE valueof 0.204
关键词：Inflation Rate Forecasting; Backpropagation Neural Network;Sugeno FIS; RMSE (Root Mean Square Error).