Nowcasting GDP using machine-learning algorithms: A real-time assessment
Can machine-learning algorithms help central banks understand the current state of the economy? Our results say yes! We contribute to the emerging literature on forecasting macroeconomic variables using machine-learning algorithms by testing the nowcast performance of common algorithms in a full ‘re...
Gespeichert in:
| Veröffentlicht in: | International journal of forecasting 2021-04, Vol.37 (2), p.941-948 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 948 |
|---|---|
| container_issue | 2 |
| container_start_page | 941 |
| container_title | International journal of forecasting |
| container_volume | 37 |
| creator | Richardson, Adam van Florenstein Mulder, Thomas Vehbi, Tuğrul |
| description | Can machine-learning algorithms help central banks understand the current state of the economy? Our results say yes! We contribute to the emerging literature on forecasting macroeconomic variables using machine-learning algorithms by testing the nowcast performance of common algorithms in a full ‘real-time’ setting—that is, with real-time vintages of New Zealand GDP growth (our target variable) and real-time vintages of around 600 predictors. Our results show that machine-learning algorithms are able to significantly improve over a simple autoregressive benchmark and a dynamic factor model. We also show that machine-learning algorithms have the potential to add value to, and in one case improve on, the official forecasts of the Reserve Bank of New Zealand. |
| doi_str_mv | 10.1016/j.ijforecast.2020.10.005 |
| format | Article |
| fullrecord | <record><control><sourceid>gale_cross</sourceid><recordid>TN_cdi_gale_incontextgauss__A652857486</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A652857486</galeid><els_id>S016920702030159X</els_id><sourcerecordid>A652857486</sourcerecordid><originalsourceid>FETCH-LOGICAL-c414t-81bb4698e6760050bc16728a34ccaccbd95ac1ad6961f976ec9ccca1784d36563</originalsourceid><addsrcrecordid>eNqFkE1OwzAQhS0EEqVwh6zYOdhpYjvsSoFSCQELWFuOM0kd5QfZLj-34SycDFtFYslqRjPfG715CCWUpJRQdtGlpmsmC1o5n2Yki-OUkOIAzajgGRYZIYdoFtASZ4STY3TiXEcCwSmdoc3D9B6lZmyT9fVTsnOxG5TemhFwD8qOcaD6drLGbwd3mSy_vyyoHnszQKKcA-cGGP0pOmpU7-Dst87Ry-3N8-oO3z-uN6vlPdY5zT0WtKpyVgpgnAUTpNKU8UyoRa610rqqy0JpqmpWMtqUnIEuddhQLvJ6wQq2mKPz_d1W9SDNqKfRw4dv1c45KZesyETBcxFBsQe1nZyz0MhXawZlPyUlMmYnO_mXnYzZxU0wFaRXeymER94MWOm0gVFDbQLtZT2Z_4_8AB7gfek</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Nowcasting GDP using machine-learning algorithms: A real-time assessment</title><source>Elsevier ScienceDirect Journals</source><creator>Richardson, Adam ; van Florenstein Mulder, Thomas ; Vehbi, Tuğrul</creator><creatorcontrib>Richardson, Adam ; van Florenstein Mulder, Thomas ; Vehbi, Tuğrul</creatorcontrib><description>Can machine-learning algorithms help central banks understand the current state of the economy? Our results say yes! We contribute to the emerging literature on forecasting macroeconomic variables using machine-learning algorithms by testing the nowcast performance of common algorithms in a full ‘real-time’ setting—that is, with real-time vintages of New Zealand GDP growth (our target variable) and real-time vintages of around 600 predictors. Our results show that machine-learning algorithms are able to significantly improve over a simple autoregressive benchmark and a dynamic factor model. We also show that machine-learning algorithms have the potential to add value to, and in one case improve on, the official forecasts of the Reserve Bank of New Zealand.</description><identifier>ISSN: 0169-2070</identifier><identifier>EISSN: 1872-8200</identifier><identifier>DOI: 10.1016/j.ijforecast.2020.10.005</identifier><language>eng</language><publisher>Elsevier B.V</publisher><subject>Algorithms ; Analysis ; Central banks ; Data mining ; Forecast evaluation ; Forecasting practice ; Gross domestic product ; Machine learning ; Macroeconomic forecasting ; Nowcasting</subject><ispartof>International journal of forecasting, 2021-04, Vol.37 (2), p.941-948</ispartof><rights>2020 International Institute of Forecasters</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c414t-81bb4698e6760050bc16728a34ccaccbd95ac1ad6961f976ec9ccca1784d36563</citedby><cites>FETCH-LOGICAL-c414t-81bb4698e6760050bc16728a34ccaccbd95ac1ad6961f976ec9ccca1784d36563</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S016920702030159X$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,776,780,3536,27903,27904,65309</link.rule.ids></links><search><creatorcontrib>Richardson, Adam</creatorcontrib><creatorcontrib>van Florenstein Mulder, Thomas</creatorcontrib><creatorcontrib>Vehbi, Tuğrul</creatorcontrib><title>Nowcasting GDP using machine-learning algorithms: A real-time assessment</title><title>International journal of forecasting</title><description>Can machine-learning algorithms help central banks understand the current state of the economy? Our results say yes! We contribute to the emerging literature on forecasting macroeconomic variables using machine-learning algorithms by testing the nowcast performance of common algorithms in a full ‘real-time’ setting—that is, with real-time vintages of New Zealand GDP growth (our target variable) and real-time vintages of around 600 predictors. Our results show that machine-learning algorithms are able to significantly improve over a simple autoregressive benchmark and a dynamic factor model. We also show that machine-learning algorithms have the potential to add value to, and in one case improve on, the official forecasts of the Reserve Bank of New Zealand.</description><subject>Algorithms</subject><subject>Analysis</subject><subject>Central banks</subject><subject>Data mining</subject><subject>Forecast evaluation</subject><subject>Forecasting practice</subject><subject>Gross domestic product</subject><subject>Machine learning</subject><subject>Macroeconomic forecasting</subject><subject>Nowcasting</subject><issn>0169-2070</issn><issn>1872-8200</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNqFkE1OwzAQhS0EEqVwh6zYOdhpYjvsSoFSCQELWFuOM0kd5QfZLj-34SycDFtFYslqRjPfG715CCWUpJRQdtGlpmsmC1o5n2Yki-OUkOIAzajgGRYZIYdoFtASZ4STY3TiXEcCwSmdoc3D9B6lZmyT9fVTsnOxG5TemhFwD8qOcaD6drLGbwd3mSy_vyyoHnszQKKcA-cGGP0pOmpU7-Dst87Ry-3N8-oO3z-uN6vlPdY5zT0WtKpyVgpgnAUTpNKU8UyoRa610rqqy0JpqmpWMtqUnIEuddhQLvJ6wQq2mKPz_d1W9SDNqKfRw4dv1c45KZesyETBcxFBsQe1nZyz0MhXawZlPyUlMmYnO_mXnYzZxU0wFaRXeymER94MWOm0gVFDbQLtZT2Z_4_8AB7gfek</recordid><startdate>20210401</startdate><enddate>20210401</enddate><creator>Richardson, Adam</creator><creator>van Florenstein Mulder, Thomas</creator><creator>Vehbi, Tuğrul</creator><general>Elsevier B.V</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20210401</creationdate><title>Nowcasting GDP using machine-learning algorithms: A real-time assessment</title><author>Richardson, Adam ; van Florenstein Mulder, Thomas ; Vehbi, Tuğrul</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c414t-81bb4698e6760050bc16728a34ccaccbd95ac1ad6961f976ec9ccca1784d36563</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Algorithms</topic><topic>Analysis</topic><topic>Central banks</topic><topic>Data mining</topic><topic>Forecast evaluation</topic><topic>Forecasting practice</topic><topic>Gross domestic product</topic><topic>Machine learning</topic><topic>Macroeconomic forecasting</topic><topic>Nowcasting</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Richardson, Adam</creatorcontrib><creatorcontrib>van Florenstein Mulder, Thomas</creatorcontrib><creatorcontrib>Vehbi, Tuğrul</creatorcontrib><collection>CrossRef</collection><jtitle>International journal of forecasting</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Richardson, Adam</au><au>van Florenstein Mulder, Thomas</au><au>Vehbi, Tuğrul</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Nowcasting GDP using machine-learning algorithms: A real-time assessment</atitle><jtitle>International journal of forecasting</jtitle><date>2021-04-01</date><risdate>2021</risdate><volume>37</volume><issue>2</issue><spage>941</spage><epage>948</epage><pages>941-948</pages><issn>0169-2070</issn><eissn>1872-8200</eissn><abstract>Can machine-learning algorithms help central banks understand the current state of the economy? Our results say yes! We contribute to the emerging literature on forecasting macroeconomic variables using machine-learning algorithms by testing the nowcast performance of common algorithms in a full ‘real-time’ setting—that is, with real-time vintages of New Zealand GDP growth (our target variable) and real-time vintages of around 600 predictors. Our results show that machine-learning algorithms are able to significantly improve over a simple autoregressive benchmark and a dynamic factor model. We also show that machine-learning algorithms have the potential to add value to, and in one case improve on, the official forecasts of the Reserve Bank of New Zealand.</abstract><pub>Elsevier B.V</pub><doi>10.1016/j.ijforecast.2020.10.005</doi><tpages>8</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0169-2070 |
| ispartof | International journal of forecasting, 2021-04, Vol.37 (2), p.941-948 |
| issn | 0169-2070 1872-8200 |
| language | eng |
| recordid | cdi_gale_incontextgauss__A652857486 |
| source | Elsevier ScienceDirect Journals |
| subjects | Algorithms Analysis Central banks Data mining Forecast evaluation Forecasting practice Gross domestic product Machine learning Macroeconomic forecasting Nowcasting |
| title | Nowcasting GDP using machine-learning algorithms: A real-time assessment |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-23T23%3A54%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Nowcasting%20GDP%20using%20machine-learning%20algorithms:%20A%C2%A0real-time%20assessment&rft.jtitle=International%20journal%20of%20forecasting&rft.au=Richardson,%20Adam&rft.date=2021-04-01&rft.volume=37&rft.issue=2&rft.spage=941&rft.epage=948&rft.pages=941-948&rft.issn=0169-2070&rft.eissn=1872-8200&rft_id=info:doi/10.1016/j.ijforecast.2020.10.005&rft_dat=%3Cgale_cross%3EA652857486%3C/gale_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_galeid=A652857486&rft_els_id=S016920702030159X&rfr_iscdi=true |