Colombian economic activity nowcasting: addressing nonlinearities and high dimensionality through machine-learning
Códigos JEL.: C45, C52, C53, E37, E32
- Autores:
-
Rincón Briceño, Juan José
- Tipo de recurso:
- Work document
- Fecha de publicación:
- 2025
- Institución:
- Universidad de los Andes
- Repositorio:
- Séneca: repositorio Uniandes
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.uniandes.edu.co:1992/76235
- Acceso en línea:
- https://hdl.handle.net/1992/76235
- Palabra clave:
- Colombian economic activity
Nowcast
Forecast
Random forests
LSTM
Economía
- Rights
- openAccess
- License
- https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf
| id |
UNIANDES2_684cd15bcb49c6715d32949363814dbc |
|---|---|
| oai_identifier_str |
oai:repositorio.uniandes.edu.co:1992/76235 |
| network_acronym_str |
UNIANDES2 |
| network_name_str |
Séneca: repositorio Uniandes |
| repository_id_str |
|
| dc.title.none.fl_str_mv |
Colombian economic activity nowcasting: addressing nonlinearities and high dimensionality through machine-learning |
| title |
Colombian economic activity nowcasting: addressing nonlinearities and high dimensionality through machine-learning |
| spellingShingle |
Colombian economic activity nowcasting: addressing nonlinearities and high dimensionality through machine-learning Colombian economic activity Nowcast Forecast Random forests LSTM Economía |
| title_short |
Colombian economic activity nowcasting: addressing nonlinearities and high dimensionality through machine-learning |
| title_full |
Colombian economic activity nowcasting: addressing nonlinearities and high dimensionality through machine-learning |
| title_fullStr |
Colombian economic activity nowcasting: addressing nonlinearities and high dimensionality through machine-learning |
| title_full_unstemmed |
Colombian economic activity nowcasting: addressing nonlinearities and high dimensionality through machine-learning |
| title_sort |
Colombian economic activity nowcasting: addressing nonlinearities and high dimensionality through machine-learning |
| dc.creator.fl_str_mv |
Rincón Briceño, Juan José |
| dc.contributor.author.none.fl_str_mv |
Rincón Briceño, Juan José |
| dc.subject.keyword.none.fl_str_mv |
Colombian economic activity Nowcast Forecast Random forests LSTM |
| topic |
Colombian economic activity Nowcast Forecast Random forests LSTM Economía |
| dc.subject.themes.none.fl_str_mv |
Economía |
| description |
Códigos JEL.: C45, C52, C53, E37, E32 |
| publishDate |
2025 |
| dc.date.accessioned.none.fl_str_mv |
2025-06-05T18:58:13Z |
| dc.date.available.none.fl_str_mv |
2025-06-05T18:58:13Z |
| dc.date.issued.none.fl_str_mv |
2025-06 |
| dc.type.spa.fl_str_mv |
Documento de trabajo |
| dc.type.driver.spa.fl_str_mv |
info:eu-repo/semantics/workingPaper |
| dc.type.version.none.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
| dc.type.coar.spa.fl_str_mv |
http://purl.org/coar/resource_type/c_8042 |
| dc.type.coarversion.none.fl_str_mv |
http://purl.org/coar/version/c_970fb48d4fbd8a85 |
| dc.type.content.spa.fl_str_mv |
Text |
| dc.type.redcol.spa.fl_str_mv |
http://purl.org/redcol/resource_type/WP |
| format |
http://purl.org/coar/resource_type/c_8042 |
| status_str |
publishedVersion |
| dc.identifier.issn.none.fl_str_mv |
1657-7191 |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/1992/76235 |
| identifier_str_mv |
1657-7191 |
| url |
https://hdl.handle.net/1992/76235 |
| dc.language.iso.none.fl_str_mv |
eng |
| language |
eng |
| dc.relation.ispartofseries.none.fl_str_mv |
Documentos CEDE; 2025-16 |
| dc.rights.uri.none.fl_str_mv |
https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf |
| dc.rights.accessrights.spa.fl_str_mv |
info:eu-repo/semantics/openAccess |
| dc.rights.coar.spa.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| rights_invalid_str_mv |
https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf http://purl.org/coar/access_right/c_abf2 |
| eu_rights_str_mv |
openAccess |
| dc.format.extent.none.fl_str_mv |
63 páginas |
| dc.format.mimetype.none.fl_str_mv |
application/pdf |
| institution |
Universidad de los Andes |
| bitstream.url.fl_str_mv |
https://repositorio.uniandes.edu.co/bitstreams/8a1239c2-3281-4250-a258-c1ed65b9e82e/download https://repositorio.uniandes.edu.co/bitstreams/5f930aea-1b43-4522-b09e-362b0cffa9b2/download https://repositorio.uniandes.edu.co/bitstreams/fb10c74b-cd0e-4d61-8d17-48337a41d9d0/download https://repositorio.uniandes.edu.co/bitstreams/13dec739-72a7-481b-adaf-4c63ad8622f2/download |
| bitstream.checksum.fl_str_mv |
b0f4ea04639955ba761b9b7581d094eb ae9e573a68e7f92501b6913cc846c39f 8fd04399b50c3808ca7fe348202112eb 4a917fa47117b2c8f3195650821729cc |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio institucional Séneca |
| repository.mail.fl_str_mv |
adminrepositorio@uniandes.edu.co |
| _version_ |
1837005379508109312 |
| spelling |
Rincón Briceño, Juan José2025-06-05T18:58:13Z2025-06-05T18:58:13Z2025-061657-7191https://hdl.handle.net/1992/76235Códigos JEL.: C45, C52, C53, E37, E32Economic decisions are made with high uncertainty about the current and recent past economic activity, due to the limited and imperfect available information. Therefore the following question arises: how can the accuracy of Colombian economic activity nowcasting be enhanced compared to traditional forecasting methods? This paper demonstrates: (a) using a risk-averse customized loss function that accounts for the agent disutility and penalizes directional discrepancies provides a useful alternative for assessing model performance by ensuring more accurate nowcasts, maximizing both precision and economic relevance. And (b) during periods of abrupt shocks and high volatility, such as the COVID-19 (2020–2021) and the post COVID-19 subsequent years (2022-2023), machine learning models outperform traditional nowcasting models.Las decisiones económicas se toman en condiciones de alta incertidumbre sobre la actividad económica actual y reciente, debido a la limitada e imperfecta información ecónomica disponible. Por lo tanto, surge la siguiente pregunta: ¿cómo se puede mejorar la fiabilidad del nowcasting de la actividad económica colombiana en comparación con los métodos tradicionales de pronóstico? Este artículo demuestra que: (a) utilizar una función de pérdida personalizada con aversión al riesgo, que considera la desutilidad del agente y penaliza discrepancias en la dirección de las predicciones, constituye una alternativa útil para evaluar el desempeño del modelo al garantizar pronósticos más fiables, maximizando tanto la precisión como la relevancia económica. Y (b) durante periodos de choques abruptos y alta volatilidad, como el COVID-19 (2020—2021) y los años posteriores (2022—2023), los modelos de aprendizaje automático superan a los modelos tradicionales de nowcasting.63 páginasapplication/pdfengDocumentos CEDE; 2025-16https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdfinfo:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Colombian economic activity nowcasting: addressing nonlinearities and high dimensionality through machine-learningDocumento de trabajoinfo:eu-repo/semantics/workingPaperinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_8042http://purl.org/coar/version/c_970fb48d4fbd8a85Texthttp://purl.org/redcol/resource_type/WPColombian economic activityNowcastForecastRandom forestsLSTMEconomíaPublicationORIGINALdcede2025-16.pdfdcede2025-16.pdfapplication/pdf16786784https://repositorio.uniandes.edu.co/bitstreams/8a1239c2-3281-4250-a258-c1ed65b9e82e/downloadb0f4ea04639955ba761b9b7581d094ebMD51LICENSElicense.txtlicense.txttext/plain; charset=utf-82535https://repositorio.uniandes.edu.co/bitstreams/5f930aea-1b43-4522-b09e-362b0cffa9b2/downloadae9e573a68e7f92501b6913cc846c39fMD52TEXTdcede2025-16.pdf.txtdcede2025-16.pdf.txtExtracted texttext/plain100849https://repositorio.uniandes.edu.co/bitstreams/fb10c74b-cd0e-4d61-8d17-48337a41d9d0/download8fd04399b50c3808ca7fe348202112ebMD53THUMBNAILdcede2025-16.pdf.jpgdcede2025-16.pdf.jpgIM Thumbnailimage/jpeg22791https://repositorio.uniandes.edu.co/bitstreams/13dec739-72a7-481b-adaf-4c63ad8622f2/download4a917fa47117b2c8f3195650821729ccMD541992/76235oai:repositorio.uniandes.edu.co:1992/762352025-06-06 04:06:30.833https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdfopen.accesshttps://repositorio.uniandes.edu.coRepositorio institucional Sénecaadminrepositorio@uniandes.edu.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 |