Vis enkel innførsel

dc.contributor.authorLarsen, Vegard H.
dc.contributor.authorThorsrud, Leif Anders
dc.date.accessioned2015-11-20T10:21:45Z
dc.date.available2015-11-20T10:21:45Z
dc.date.issued2015
dc.identifier.issn1892-2198
dc.identifier.urihttp://hdl.handle.net/11250/2364954
dc.description.abstractWe decompose a major business newspaper according to the topics it writes about, and show that the topics have predictive power for key economic variables and, especially noteworthy, for asset prices. Unexpected innovations to an aggregated news index, derived as a weighted average of the topics with the highest predictive scores, cause large and persistent economic fluctuations, a permanent increase in productivity, and are especially associated with financial markets, credit and borrowing. Unexpected innovations to asset prices, orthogonal to news shocks and labeled as noise, have only temporary positive effects.nb_NO
dc.language.isoengnb_NO
dc.publisherBI Norwegian Business Schoolnb_NO
dc.relation.ispartofseriesCAMP Working Paper Series;6/2015
dc.subjectMachine learningnb_NO
dc.subjectLatent Dirichlet Allocation (LDA)nb_NO
dc.subjectBayesian Dynamic Threshold Modelnb_NO
dc.subjectBusiness Cyclesnb_NO
dc.titleThe Value of Newsnb_NO
dc.typeWorking papernb_NO
dc.source.pagenumber51nb_NO
dc.source.issue6/2015nb_NO


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel