dc.rights.license | Atribución-NoComercial-SinDerivadas 4.0 Internacional |
dc.contributor.advisor | Jalil Barney, Munir Andrés |
dc.contributor.author | Pedraza Quiñones, Sergio Daniel |
dc.date.accessioned | 2021-01-15T21:10:30Z |
dc.date.available | 2021-01-15T21:10:30Z |
dc.date.issued | 2020-10-16 |
dc.identifier.uri | https://repositorio.unal.edu.co/handle/unal/78785 |
dc.description.abstract | El documento presenta un índice de incertidumbre de política económica (o índice EPU) para Colombia construido mediante técnicas de Procesamiento de Lenguaje Natural (NLP). La hipótesis es que existe una relación significativa entre el índice EPU y variables como el crecimiento y la inflación y que choques de incertidumbre de política económica tienen un efecto adverso en el desempeño económico del país. Así mismo, se presume que un índice
construido con técnicas de NLP recoge de mejor forma la información sobre incertidumbre que un índice construido simplemente con la búsqueda de palabras clave. El uso de herramientas de NLP, así como de modelos de aprendizaje supervisado y no supervisado constituye, tan lejos como sé, la primera aplicación de este tipo de modelos para Colombia en relación con la medición de incertidumbre de política económica. Se obtiene que el índice EPU, construido con un modelo de aprendizaje supervisado, exhibe la mejor capacidad explicativa con respecto a diversos indicadores macroeconómicos. Esta investigación se desarrolla con base en los artículos del archivo del periódico El Tiempo, el único en Colombia que cuenta con una hemeroteca digital desde el año 2000 hasta 2018, periodo comprendido por el estudio. |
dc.description.abstract | This document introduces an economic policy uncertainty index (or EPU index) for Colombia built on Natural Language Processing (NLP) techniques. The hypothesis is that there exists a significant relationship between the EPU index and indicators like economic growth and inflation, and that economic policy uncertainty shocks have a prejudicial effect over the country’s economic performance. Likewise, it is supposed that an index built on NLP techniques captures more appropriately information about uncertainty than an index built just through search for keywords. The use of NLP tools, as well as of supervised and unsupervised learning models constitutes, as far as I know, the first application of this kind of models for Colombia, within the scope of the measuring economic policy uncertainty. It is obtained that EPU index, when built with a supervised learning model, exhibits the best explaining capability with respect to diverse macroeconomic indicators. This research is done by the means of extracting articles from El Tiempo newspaper, the only one in Colombia that holds a digital newspaper library from 2000 until 2018, which is the period covered by the study. |
dc.format.extent | 43 |
dc.format.mimetype | application/pdf |
dc.language.iso | spa |
dc.rights | Derechos reservados - Universidad Nacional de Colombia |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ |
dc.subject.ddc | 330 - Economía |
dc.title | Estimación de un índice de incertidumbre de política económica para Colombia mediante el uso de NLP y modelos de aprendizaje supervisado y no supervisado |
dc.type | Trabajo de grado - Maestría |
dc.rights.spa | Acceso abierto |
dc.description.additional | Línea de Investigación: Ciencia de Datos |
dc.type.driver | info:eu-repo/semantics/masterThesis |
dc.type.version | info:eu-repo/semantics/acceptedVersion |
dc.publisher.program | Bogotá - Ciencias Económicas - Maestría en Ciencias Económicas |
dc.description.degreelevel | Maestría |
dc.publisher.department | Escuela de Economía |
dc.publisher.branch | Universidad Nacional de Colombia - Sede Bogotá |
dc.relation.references | Azqueta-Gavaldon, A. (2017). Developing News-Based Economic Policy Uncertainty Index with Unsupervised Machine Learning. Economics Letters, 158, 47–50. Retrieved from http://www.sciencedirect.com/science/journal/01651765 |
dc.relation.references | Baker, S. R., Bloom, N., & Davis, S. J. (2016). Measuring Economic Policy Uncertainty. Quarterly Journal of Economics, 131(4), 1593–1636. Retrieved from https://academic.oup.com/qje/issue |
dc.relation.references | Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet allocation. In Journal of Machine Learning Research (Vol. 3). https://doi.org/10.1016/b978-0-12-411519-4.00006-9 |
dc.relation.references | Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324 |
dc.relation.references | Gil, M., Silva D. (2018). Economic Policy Uncertainty Indicex for Colombia. Retreived from https://www.policyuncertainty.com/colombia.html |
dc.relation.references | Halko, N., Martinsson, P. G., & Tropp, J. A. (2011). Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions. SIAM Review, 53(2), 217–288. https://doi.org/10.1137/090771806 |
dc.relation.references | Hodrick, R. J., & Prescott, E. C. (1997). Postwar U.S. Business Cycles: An Empirical Investigation. Journal of Money, Credit and Banking, 29(1), 1–16. https://doi.org/10.2307/2953682 |
dc.relation.references | International Monetary Fund. (2016). World Economic Outlook: Too Slow for Too Long. Washington, April 2016. Retrieved from https://www.imf.org/en/Publications/WEO/Issues/2016/12/31/Too-Slow-for-Too-Long |
dc.relation.references | Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. 32nd International Conference on Machine Learning, ICML 2015, 1, 448–456. International Machine Learning Society (IMLS). |
dc.relation.references | Luetkepohl, H. (2005). The New Introduction to Multiple Time Series Analysis. In New Introduction to Multiple Time Series Analysis. https://doi.org/10.1007/978-3-540-27752-1 |
dc.relation.references | Orphanides, A., & Wei, M. (2012). Evolving Macroeconomic Perceptions and the Term Structure of Interest Rates. Journal of Economic Dynamics and Control, 36(2), 239–254. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&db=eoh&AN=1278070&lang=es&site=ehost-live |
dc.relation.references | Raschka, S. (2014). Naive Bayes and Text Classification {I} - Introduction and Theory. CoRR, abs/1410.5. Retrieved from http://arxiv.org/abs/1410.5329 |
dc.relation.references | Skansi, S. (2018). Introduction to Deep Learning (1st ed.). https://doi.org/10.1007/978-3-319-73004-2 |
dc.relation.references | Tobback, E., Naudts, H., Daelemans, W., Fortuny, E. J. de, & Martens, D. (2018). Belgian Economic Policy Uncertainty Index: Improvement through Text Mining. International Journal of Forecasting, 34(2), 355–365. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&db=eoh&AN=1722032&lang=es&site=ehost-live |
dc.relation.references | Weiss, S., Indurkhya, N., & Zhang, T. (2015). Fundamentals of Predictive Text Mining. https://doi.org/10.1007/978-1-4471-6750-1 |
dc.rights.accessrights | info:eu-repo/semantics/openAccess |
dc.subject.proposal | Uncertainty |
dc.subject.proposal | Incertidumbre |
dc.subject.proposal | Neural Networks |
dc.subject.proposal | Redes Neuronales |
dc.subject.proposal | Natural Language Processing |
dc.subject.proposal | Procesamiento de Lenguaje Natural |
dc.subject.proposal | Política económica |
dc.subject.proposal | Economic policy |
dc.subject.proposal | Inflation |
dc.subject.proposal | Inflación |
dc.subject.proposal | Crecimiento económico |
dc.subject.proposal | Economic growth |
dc.type.coar | http://purl.org/coar/resource_type/c_bdcc |
dc.type.coarversion | http://purl.org/coar/version/c_ab4af688f83e57aa |
dc.type.content | Text |
oaire.accessrights | http://purl.org/coar/access_right/c_abf2 |