Rehim KilicThis paper investigates whether the “virtue of complexity” (VoC), documented in equity return prediction, extends to exchange rate forecasting. Using nonlinear Ridge regressions with Random Fourier Features (Ridge–RFF), we compare the predictive performance of complex models against linear regression and the robust random walk benchmark.
This study introduces a novel approach to dictionary-based sentiment analysis that extracts valuable insights from economic newspaper articles in the euro area without requiring article translation. We develop sentiment indices that accurately measure economic, labour, and inflation perceptions in Germany, France, Italy, and Spain using native-language texts. The aggregation of these country-specific sentiments provides a reliable indicator for the euro area as a whole, demonstrating the effectiveness of our approach in several nowcasting and forecasting experiments.
How large are the distributional effects of monetary policy in the euro area? Does heterogeneity matter for monetary policy? We answer these questions based on the results of research projects conducted at the ECB under the aegis of a dedicated research task force. A monetary policy easing causes a temporary reduction in consumption inequality; this is the case for both conventional and unconventional monetary policy.
This study introduces a novel approach to dictionary-based sentiment analysis that extracts valuable insights from economic newspaper articles in the euro area without requiring article translation. We develop sentiment indices that accurately measure economic, labour, and inflation perceptions in Germany, France, Italy, and Spain using native-language texts. The aggregation of these country-specific sentiments provides a reliable indicator for the euro area as a whole, demonstrating the effectiveness of our approach in several nowcasting and forecasting experiments.
How large are the distributional effects of monetary policy in the euro area? Does heterogeneity matter for monetary policy? We answer these questions based on the results of research projects conducted at the ECB under the aegis of a dedicated research task force. A monetary policy easing causes a temporary reduction in consumption inequality; this is the case for both conventional and unconventional monetary policy.
Manufacturing activity in the euro area rebounded in early 2025, while services activity slowed, marking a reversal of the trends observed in the previous two years. This box analyses the role of frontloading effects and trade policy uncertainty in driving recent production dynamics. It argues that manufacturing benefited temporarily from frontloading ahead of US tariff measures, while services were more directly affected by rising trade policy uncertainty. In particular, hard data reveal that manufacturing subsectors with higher exposure to the United States (e.g.
This box describes the Eurosystem liquidity conditions and monetary policy operations in the third and fourth reserve maintenance periods of 2025, from 23 April to 29 July 2025.
This article uses a suite of macroeconomic models to assess the economic impacts of an increase in euro area defence spending. Multipliers of government purchases average just below 1, and there is notable model uncertainty. Pressures on HICP (Harmonised Index of Consumer Prices) inflation increase only gradually over time. An analysis of the transmission channels suggests that private sector expectations of higher future interest rates and taxes may substantially reduce fiscal multipliers.
In surveys with information provision experiments, researchers can observe how people change beliefs, and sometimes also actions, after having been confronted with information. This article interprets information provision experiments from the perspective of the theory of rational inattention, discussing what survey findings tell us about economic behaviour outside the survey and deriving implications for central bank communication.
Vitaly M. Bord, Agnes Kovacs, and Patrick MoranIn the United States, credit card companies frequently use machine learning algorithms to proactively raise credit limits for borrowers. In contrast, an increasing number of countries have begun to prohibit credit limit increases initiated by banks rather than consumers.
