Forecasting activities have historically played and will continue to play an important role in the Commission’s macro-economic activities. The European Commission Joint Research Centre contributes in the monitoring of macro-economic outcomes and in advising policy makers.
The Nowcasting group at JRC, in cooperation with partner institutions, develops econometric techniques and applies them for nowcasting and forecasting. Nowcasting techniques exploit data that become available in real time (including Big Data), so they can detect real time developments (for instance on GDP). This dashboard provides on the activities carried out with the group.
All content of this site is for expositional purposes, and does not include judgement. This website is a research website and should not be considered as representative of the European Commission’s official position. The European Commission shall not be liable for any consequence stemming from the reuse of this content.
Last forecast update on
Select the following paramaters:
- Model : uncoditional BVAR or BVAR conditional to future scenarios on energy markets and monetary policy.
- Variable : HICP, HICPxef (excluding food and energy prices) or HICPxefun (excluding energy and unprocessed food).
Historical Decomposition
Decompose model fit by the contribution of variable group (available only for the unconditional BVAR model). The solid line is the observed inflation level (annual % change, in deviations from the mean and from the contribution of initial conditions).
Download historical decomposition by individual variable
Forecast Error Variance Decomposition
Forecast Error Variance Decomposition (FEVD) at different horizons.
Model
Bayesian vector autoregressive (BVAR) model with 13 lags for the monthly model and 5 lags for the quarterly model as in Giannone et al. (2014).
To overcome the “curse of dimensionality” we shrink the model’s coefficients toward a naïve and parsimonious random walk with drift model. We use a Minnesota prior as De Mol et al. (2008) where the direction of shrinkage is controlled by a set of hyper-parameters: the overall tightness of the prior, the prior tightness on the lags greater than one, the sum-of-coefficient prior, the co-persistence prior, the prior on the covariance matrix. We maximize the log-likelihood via an iterative approach. Given the optimal set of hyper-parameters, we draw from the posterior distribution and get a density distribution for each variable and forecasting horizon.
All content of this site is for expositional purposes, and does not include judgement. This website is a research website and should not be considered as representative of the European Commission’s official position. The European Commission shall not be liable for any consequence stemming from the reuse of this content.
Last forecast update on
Research
Events
The events were organized by the ‘Big Data and Economic Forecasting’ team within the Centre for Advanced Studies of the EC-JRC. The work is now carried out by the Nowcasting team:
- March 16-17, 2021: second Big Data and Economic Forecasting workshop: Agenda Recording Day 1 Recording Day 2
- May 16-17, 2019: first Big Data and Economic Forecasting workshop: Agenda Call for Papers
- June 11-12, 2018: kick-off workshop Big Data and Economic Forecasting Agenda
Peer-reviewed scientific publications
Selected publications on macro-economic fore/now-casting (including also the work carried out within the bigNOMICS prjoect):
2024
- Huber, Onorante, Pfarrhofer 202X. Forecasting euro area inflation using a huge panel of survey expectations, International Journal of Forecasting , forthcoming.
- Barbaglia, Manzan, Tosetti, 202X. Household Debt and Economic Growth in Europe, Macroeconomic Dynamics, forthcoming.
- Barbaglia, Consoli, Manzan, 2024. Forecasting GDP in Europe with Textual Data, Journal of Applied Econometrics , 39(2), 338-355.
2023
- Barbaglia, Consoli, Manzan, 2023. Forecasting with Economic News, Journal of Business & Economic Statistics , 41(3), 708-719.
- Barbaglia, Frattarolo, Onorante, Pericoli, Ratto, Tiozzo Pezzoli, 2023. Testing Big Data in a Big Crisis: Nowcasting under COVID-19, International Journal of Forecasting, 39(4), 1548-1563.
- Barbaglia, Manzan, Tosetti, 2023. Forecasting Loan Default in Europe with Machine Learning, Journal of Financial Econometrics , 21(2), 569–596.
- Huber, Koop, Onorante, Pfarrhofer, Schreiner, 2023. Nowcasting in a Pandemic using Non-Parametric Mixed Frequency VARs, Journal of Econometrics, 232(1), 52-69.
- Deiana, Mazzarella, Meroni, Tiozzo Pezzoli, 2023. The unexpected influencer: Pope Francis and European perceptions of the recent refugee crisis, Oxford Economic Papers, 75 (1), 75-95
2022
- Consoli, Barbaglia, Manzan, 2022. Fine-Grained, Aspect-Based Sentiment Analysis on Economic and Financial Lexicon, Knowledge-Based Systems , 247(8), 108781.
- Consoli, Tiozzo Pezzoli, Tosetti, 2022. Neural Forecasting of the Italian Sovereign Bond Market with Economic News, Journal of the Royal Statistical Society – Series A (Statistics in Society) , 185, (Suppl. 2), S197–S224.
- Tiozzo Pezzoli, Tosetti, 2022. Seismonomics: Listening to the Heartbeat of the Economy, Journal of the Royal Statistical Society – Series A (Statistics in Society) , 185 (Suppl. 2), S288– S309.
2021
- Consoli, Tiozzo Pezzoli, Tosetti, 2021. Emotions in Macroeconomic News and their Impact on the European Bond Market, Journal of International Money and Finance , 118, 102472.
- Hauzenberger, Huber, Onorante, 2021. Combining shrinkage and sparsity in conjugate vector autoregressive models, Journal of Applied Econometrics , 36(3), 304-327.
- Huber, Koop, Onorante, 2021. Inducing Sparsity and Shrinkage in Time-Varying Parameter Models, Journal of Business & Economic Statistics , 39(3), 669-683.
2020
- Crespo Cuaresma, Huber, Onorante, 2020. Fragility and the effect of international uncertainty shocks, Journal of International Money and Finance , 108(C), 102151.
All content of this site is for expositional purposes, and does not include judgement. This website is a research website and should not be considered as representative of the European Commission’s official position. The European Commission shall not be liable for any consequence stemming from the reuse of this content.
Nowcasting team
- Luca Onorante
- Luca Barbaglia
- Marco Ratto
- Luigi Longo
- Konstantin Boss
The Nowcasting team operates within the Economy and Finance unit at the European Commission Joint Research Centre.
E-mail: JRC-NOWCASTING@ec.europa.eu.
All content of this site is for expositional purposes, and does not include judgement. This website is a research website and should not be considered as representative of the European Commission’s official position. The European Commission shall not be liable for any consequence stemming from the reuse of this content.