Forecasting euro area inflation with machine-learning models

The strategy review concluded in 2021 highlighted how most Eurosystem models used to forecast inflation are linear.

Metadata
Provider: 
ECBECB
URL: 
https://www.ecb.europa.eu//pub/economic-research/resbull/2023/html/ecb.rb231017~b910853393.en.htmlhttps://www.ecb.europa.eu//pub/economic-research/resbull/2023/html/ecb.rb231017~b910853393.en.html
Retrieved on: 
Mercredi, janvier 3, 2024
Information
Tags: 
Medeiros, Chapter Two, Forecasting, Economy, Inflation, Linearity, Directorate, Uncertainty, Machine learning, Coronavirus, Chart, Travel, Information, HICP, NBER, Economics, Business, Random forest, Prevalence, Speech, Unemployment, SPF, Eurozone, Journal, Giannone, EDS, QRF, Central bank, Business cycle, Linear model, Great Recession, European Central Bank, American Economic Journal, Time, Shapley, ECB, Economic statistics, Euro, Policy, Macroeconomics, Global recession, Nickel, Role, COVID-19, International Economic Review, Orientation, Canadian International Council, Conceptual model, Textile
Geotags: 
NO, PHILLIPS, FOREST
Résumé
Key Points: 
  • The strategy review concluded in 2021 highlighted how most Eurosystem models used to forecast inflation are linear.
  • Linear models assume that changes in, for example, wages, always have the same fixed, proportional effect on inflation.
Copyright: 
2024 ECB. All Rights Reserved.