| dc.contributor.author | Ellingsen, Jon | |
| dc.contributor.author | Larsen, Vegard H. | |
| dc.contributor.author | Thorsrud, Leif Anders | |
| dc.date.accessioned | 2020-10-15T05:34:18Z | |
| dc.date.available | 2020-10-15T05:34:18Z | |
| dc.date.issued | 2020-10-08 | |
| dc.identifier.uri | https://hdl.handle.net/11250/2682897 | |
| dc.description.abstract | Using 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 U.S. 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.iso | eng | en_US |
| dc.publisher | BI Norwegian Business School | en_US |
| dc.relation.ispartofseries | CAMP Working Paper Series;08/2020 | |
| dc.subject | Forecasting | en_US |
| dc.subject | Real-time | en_US |
| dc.subject | Machine Learning | en_US |
| dc.subject | News | en_US |
| dc.subject | Text data | en_US |
| dc.title | News media vs. FRED-MD for macroeconomic forecasting | en_US |
| dc.type | Working paper | en_US |
| dc.source.pagenumber | 45 | en_US |
