A forecasting the consumer price index using time series model

This article examines the behavior of consumer price index in Ukraine for period from January 2010 to September 2020. The characteristics initial time series, analysis autocorrelation functions made it possible reveal tendency their development and presence annual seasonality. To model forecast next months, two types models were used: additive ARIMA*ARIMAS model, better known as Box-Jenkins exponential smoothing with seasonality estimate Holt-Winters. As a result using STATISTICA package, most adequate built, reflecting monthly dynamics Ukraine. inflation was carried out on basis Holt-Winters which has minimum error.