<![CDATA[One of the important indicators on a country's economy is inflation. Inflation is an increase in the price of goods and services in general and continuously over a certain period of time. Various studies have been conducted to predict inflation, both using conventional methods and those using artificial intelligence. This research uses the ARIMA method specifically to help the government in monitoring fiscal and monetary policies so that they are more responsive to the threat of inflation, such as interest rate adjustments or basic commodity price policies. The main objective of this study is to obtain a model that can be used to predict inflation in Indonesia with a high degree of accuracy. The results of the descriptive analysis show that the highest inflation in Indonesia occurred during the monetary crisis, namely in February 1998, which was 12.76, while the highest average inflation occurred in 1998 at 4.818. ARIMA modeling for inflation results in an ARIMA([1,3,5,8,48],0,0) model with an outlier , the model satisfies the residual white noise assumption, but does not meet the normally distributed residual assumption. Based on the RMSE and MAPE values, the results show that the RMSE data out sample has a smaller RMSE value when compared to the in sample data, while the MAPE value is smaller in sample data when compared to the out sample data]]>
Copyrights © 2025
