INDONESIAN CONSUMER PRICE INDEX (CPI) FORECASTING USING AN EXPONENNTIAL SMOOTHING-STATE SPACE MODEL

INDONESIAN CONSUMER PRICE INDEX (CPI) FORECASTING USING AN EXPONENNTIAL SMOOTHING-STATE SPACE MODEL

Price Consumer Index (PCI), Forecasting of Indonesia PCI, Exponential Smoothing-State Space, ETS (M,N,N).

The Consumer Price Index (CPI) is one of the important economic indicators that can provide information about the development of the price of goods/services paid by consumers. The CPI has a relationship in determining inflation so inflation and CPI are important variables in seeing the development of the economy in a particular country or city. The CPI and inflation are so important that many researchers have studied inflation and CPI. The purpose of this study is to predict the value of Indonesia's monthly CPI with a simple, easy, and highly accurate forecasting model using R package statistics software. The CPI data used was the monthly CPI data from BPS from January 2014 to August 2024. The forecasting model used in this study was the ETS(M,N,N) model. The determination of the best ETS model is based on the minimum value of the Akaike information criteria (AIC) and Bayesian information criteria (BIC). The best model used was the ETS (M,N,N) model with a smoothing parameter (α) of 0.9933, a root mean square error (RMSE) of 3.275868, and a mean absolute percentile error (MAPE) of 0.6595211%. The forecasting results for the next four periods, namely September-December 2024, are around the value of 106,0602.

Jauharul Maknunah1, Mohamad As’ad2*, Sigit Setyowibowo3, Eni Farida4
Indah Dwi Mumpuni5

https://jurnal.stie-aas.ac.id/index.php/IJEBAR

2024-12-19

PERI IRAWAN

PDF

ENGLISH

TEXT