Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/322058 
Erscheinungsjahr: 
2025
Schriftenreihe/Nr.: 
ECB Working Paper No. 3047
Verlag: 
European Central Bank (ECB), Frankfurt a. M.
Zusammenfassung: 
Word embeddings are vectors of real numbers associated with words, designed to capture semantic and syntactic similarity between the words in a corpus of text. We estimate the word embeddings of the European Central Bank's introductory statements at monetary policy press conferences by using a simple natural language processing model (Word2Vec), only based on the information and model parameters available as of each press conference. We show that a measure based on such embeddings contributes to improve core inflation forecasts multiple quarters ahead. Other common textual analysis techniques, such as dictionary-based metrics or sentiment metrics do not obtain the same results. The information contained in the embeddings remains valuable for out-of-sample forecasting even after controlling for the central bank inflation forecasts, which are an important input for the introductory statements
Schlagwörter: 
Embeddings
forecasting
central bank texts
Inflation
central bank
economic forecasting
monetary policy
natural language processing
JEL: 
E31
E37
E58
Persistent Identifier der Erstveröffentlichung: 
ISBN: 
978-92-899-7216-1
Dokumentart: 
Working Paper

Datei(en):
Datei
Größe
1.46 MB





Publikationen in EconStor sind urheberrechtlich geschützt.