Word2Prices: embedding central bank communications for inflation prediction

Douglas Araujo, Nikola Bokan, Fabio Alberto Comazzi and Michele Lenza

No 1253, BIS Working Papers from Bank for International Settlements

Abstract: 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.

Keywords: embeddings; inflation; forecasting; central bank texts (search for similar items in EconPapers)
JEL-codes: E31 E37 E58 (search for similar items in EconPapers)
Date: 2025-03
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.bis.org/publ/work1253.pdf Full PDF document (application/pdf)
https://www.bis.org/publ/work1253.htm (text/html)

Related works:
Working Paper: Word2Prices: embedding central bank communications for inflation prediction (2025)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bis:biswps:1253

Access Statistics for this paper

More papers in BIS Working Papers from Bank for International Settlements Contact information at EDIRC.
Bibliographic data for series maintained by Martin Fessler ().