Assessing the Impact of COVID-19 on Trade: a Machine Learning Counterfactual Analysis
| dc.audience | Researchers | eng |
| dc.audience | Students | eng |
| dc.audience | Teachers | eng |
| dc.contributor.institucion | Universidad Jorge Tadeo Lozano | spa |
| dc.coverage.ciudad | Bogotá | spa |
| dc.creator | Dueñas, Marco | spa |
| dc.creator | Ortiz, Víctor | spa |
| dc.creator | Riccaboni, Massimo | spa |
| dc.creator | Serti, Francesco | spa |
| dc.date.accessioned | 2021-04-13T16:06:40Z | spa |
| dc.date.available | 2021-04-13T16:06:40Z | spa |
| dc.date.created | 2021-04-09 | spa |
| dc.description | By interpreting exporters’ dynamics as a complex learning process, this paper constitutes the first attempt to investigate the effectiveness of different Machine Learning (ML) techniques in predicting firms’ trade status. We focus on the probability of Colombian firms surviving in the export market under two different scenarios: a COVID-19 setting and a non-COVID-19 counterfactual situation. By comparing the resulting predictions, we estimate the individual treatment effect of the COVID-19 shock on firms’ outcomes. Finally, we use recursive partitioning methods to identify subgroups with differential treatment effects. We find that, besides the temporal dimension, the main factors predicting treatment heterogeneity are interactions between firm size and industry. | eng |
| dc.description.abstract | By interpreting exporters’ dynamics as a complex learning process, this paper constitutes the first attempt to investigate the effectiveness of different Machine Learning (ML) techniques in predicting firms’ trade status. We focus on the probability of Colombian firms surviving in the export market under two different scenarios: a COVID-19 setting and a non-COVID-19 counterfactual situation. By comparing the resulting predictions, we estimate the individual treatment effect of the COVID-19 shock on firms’ outcomes. Finally, we use recursive partitioning methods to identify subgroups with differential treatment effects. We find that, besides the temporal dimension, the main factors predicting treatment heterogeneity are interactions between firm size and industry. | eng |
| dc.format.extent | 31 páginas | spa |
| dc.format.mimetype | spa | |
| dc.identifier.uri | https://repositorio.redinvestigadores.org/handle/Riec/100 | spa |
| dc.language.iso | eng | eng |
| dc.relation.ispartof | Documentos de Trabajo | spa |
| dc.relation.number | No.79 | spa |
| dc.relation.repec | https://ideas.repec.org/p/rie/riecdt/79.html | spa |
| dc.relation.uri | https://arxiv.org/pdf/2104.04570.pdf | spa |
| dc.rights.accessRights | Open Access | eng |
| dc.rights.cc | Atribucion-NoComercial-CompartirIgual CC BY-NC-SA 4.0 | spa |
| dc.rights.spa | Acceso abierto | spa |
| dc.rights.uri | https://creativecommons.org/licenses/by-nc-sa/4.0/ | eng |
| dc.subject.jel | F14 - Empirical Studies of Trade | eng |
| dc.subject.jel | F17 - Trade Forecasting and Simulation | eng |
| dc.subject.jel | D22 - Firm Behavior: Empirical Analysis | eng |
| dc.subject.jel | L25 - Firm Performance: Size, Diversification, and Scope | eng |
| dc.subject.keyword | Machine Learning | eng |
| dc.subject.keyword | International Trade | eng |
| dc.subject.keyword | COVID-19 | eng |
| dc.subject.lemb | Impacto económico -- Aislamiento preventivo -- Covid 19 -- Colombia | spa |
| dc.subject.lemb | Machine Learning -- Probabilidades -- Estudios comparados -- Colombia | spa |
| dc.title | Assessing the Impact of COVID-19 on Trade: a Machine Learning Counterfactual Analysis | eng |
| dc.type | Working paper | eng |
| dc.type.hasversion | Published Version | eng |
| dc.type.spa | Documentos de Trabajo | spa |