Comparative analysis of regional inflation forecasting models

The study aims to compare approaches to forecasting the monthly level of consumer price index (CPI y/y) in the regions of the Volga Federal District using time series models and machine learning methods. This study attempts to select the most appropriate and efficient models for predicting the regional general price level index. The paper also shows the use of a combined approach, which is based on the combination of both methods. The results show that machine learning models provide more stable and accurate forecasts than econometric models - especially over long forecasting periods (6 months or more). However, for several regions, we found evidence of the effectiveness of time series models for the short term - for several regions, different specifications of extended autoregressive models perform better than the machine learning model approach when forecasting for 1 and 3 months. The results of the combined approach are comparable to the forecasts of machine learning models and more often provide more accurate forecasts for 12 and 24 months. The study showed that it was not possible to detect a sustainable effect of regional characteristics in the forecasting results caused by the specifics of the region, namely the volatility of inflation and the structure of the regional economy.