Show simple item record

dc.contributor.authorEllingsen, Jon
dc.contributor.authorLarsen, Vegard Høghaug
dc.contributor.authorThorsrud, Leif Anders
dc.date.accessioned2023-05-24T12:08:56Z
dc.date.available2023-05-24T12:08:56Z
dc.date.created2021-10-20T15:20:11Z
dc.date.issued2021
dc.identifier.issn0883-7252
dc.identifier.urihttps://hdl.handle.net/11250/3068837
dc.description.abstractUsing a unique dataset of 22.5 million news articles from the Dow Jones Newswires Archive, we perform an in depth real-time out-of-sample forecasting comparison study with one of the most widely used data sets in the newer forecasting literature, namely the FRED-MD dataset. Focusing on US GDP, consumption and investment growth, our results suggest that the news data contains information not captured by the hard economic indicators, and that the news-based data are particularly informative for forecasting consumption developments.en_US
dc.language.isoengen_US
dc.publisherWileyen_US
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internasjonal*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/deed.no*
dc.subjectForecastingen_US
dc.subjectMachine Learningen_US
dc.subjectNewsen_US
dc.subjectReal-timeen_US
dc.subjectText dataen_US
dc.titleNews media versus FRED-MD for macroeconomic forecastingen_US
dc.typePeer revieweden_US
dc.typeJournal articleen_US
dc.description.versionpublishedVersionen_US
dc.source.volume37en_US
dc.source.journalJournal of applied econometricsen_US
dc.source.issue1en_US
dc.identifier.doi10.1002/jae.2859
dc.identifier.cristin1947347
cristin.ispublishedtrue
cristin.fulltextoriginal
cristin.qualitycode2


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivatives 4.0 Internasjonal
Except where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivatives 4.0 Internasjonal