Mostrar el registro sencillo del documento
Pronóstico de la pérdida crediticia esperada de los clientes con mayor nivel de riesgo de un banco por medio de modelos paramétricos y no paramétricos
dc.rights.license | Atribución-NoComercial-SinDerivadas 4.0 Internacional |
dc.contributor.advisor | González Álvarez, Nelfi Gertrudis |
dc.contributor.author | López Avendaño, Brandon |
dc.date.accessioned | 2023-11-08T13:56:55Z |
dc.date.available | 2023-11-08T13:56:55Z |
dc.date.issued | 2023 |
dc.identifier.uri | https://repositorio.unal.edu.co/handle/unal/84912 |
dc.description | ilustraciones, diagramas |
dc.description.abstract | La pérdida crediticia esperada (ECL) permite establecer bajo la normatividad IFRS 9 el nivel de provisión y el cálculo de reservas esperadas de una entidad financiera, donde a mayor riesgo percibido, existirá un mayor nivel de provisión en los balances del banco. Se ha encontrado en la literatura que, por medio de indicadores macroeconómicos, información transaccional y sectorial, índices financieros y medidas de riesgo, es posible prever la pérdida crediticia esperada en diferentes periodos de tiempo, por lo tanto, en el presente trabajo se proponen 437 variables que han resultado ser significativas en diferentes estudios, a las cuales, se les realizó una reducción de dimensionalidad y selección de variables, resultando 10 de éstas las que mejor explican la ECL. Adicionalmente, se propusieron modelos paramétricos y no paramétricos como: Regresión Lineal Múltiple, Lasso, Ridge, Bosques Aleatorios, entre otros para pronosticar la pérdida crediticia esperada, siendo el modelo Extremely Randomized Trees (Extra Trees) el que mejor desempeño tuvo en las medidas MSE, MAE y coeficiente de determinación, con valores de 0.0078, 0.0564 y 0.9199, respectivamente. Se encontró que gran parte de los predictores presentaban relaciones no lineales con la variable respuesta que el modelo era capaz de capturar, y por medio de los valores de SHAP (Shapley Additive Explanation) se pudo evidenciar que las relaciones de las variables independientes con la ECL guardaban sentido con la teoría económica. (Texto tomado de la fuente) |
dc.description.abstract | Expected credit loss (ECL) enables financial institutions to determine the provision level and calculate expected reserves in accordance with IFRS 9 regulations. Higher perceived risk corresponds to higher provision levels recorded in the bank's balance sheets. Extensive research has shown that by utilizing macroeconomic indicators, transactional and sectorial information, financial ratios, and risk measures, it is possible to forecast the expected credit loss across different time periods. In this study, a set of 437 variables, identified as significant in previous research, underwent dimensionality reduction and variable selection procedures, resulting in the identification of 10 key predictors that best explain the ECL. Moreover, a range of parametric and non-parametric models, including Multiple Linear Regression, Lasso, Ridge, Random Forests, among others, were evaluated for their ability to forecast the expected credit loss. Among these models, the Extremely Randomized Trees (Extra Trees) model demonstrated superior performance in terms of MSE, MAE, and coefficient of determination, with values of 0.0078, 0.0564 and 0.9199, respectively. Notably, the analysis revealed that a significant number of predictors exhibited non-linear relationships with the response variable, which the Extra Trees model effectively captured. By employing SHAP values (Shapley Additive Explanation), the relationships between the independent variables and ECL were found to align with the economic theory. |
dc.format.extent | 133 páginas |
dc.format.mimetype | application/pdf |
dc.language.iso | spa |
dc.publisher | Universidad Nacional de Colombia |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ |
dc.subject.ddc | 510 - Matemáticas::519 - Probabilidades y matemáticas aplicadas |
dc.subject.ddc | 330 - Economía::332 - Economía financiera |
dc.title | Pronóstico de la pérdida crediticia esperada de los clientes con mayor nivel de riesgo de un banco por medio de modelos paramétricos y no paramétricos |
dc.type | Trabajo de grado - Maestría |
dc.type.driver | info:eu-repo/semantics/masterThesis |
dc.type.version | info:eu-repo/semantics/acceptedVersion |
dc.publisher.program | Medellín - Ciencias - Maestría en Ciencias - Estadística |
dc.coverage.country | Colombia |
dc.description.degreelevel | Maestría |
dc.description.degreename | Magister en Ciencias-Estadística |
dc.identifier.instname | Universidad Nacional de Colombia |
dc.identifier.reponame | Repositorio Institucional Universidad Nacional de Colombia |
dc.identifier.repourl | https://repositorio.unal.edu.co/ |
dc.publisher.faculty | Facultad de Ciencias |
dc.publisher.place | Medellín, Colombia |
dc.publisher.branch | Universidad Nacional de Colombia - Sede Medellín |
dc.relation.indexed | RedCol |
dc.relation.indexed | LaReferencia |
dc.relation.references | Akaike, H. (1974). A new look at the statistical model identification. IEEE Transactions on Automatic Control, 19(6), 716–723. https://doi.org/10.1109/TAC.1974.1100705 |
dc.relation.references | Altman, E. I. (1968). Financial Ratios, Discriminant Analysis and the Prediction of Corporate Bankruptcy. The Journal of Finance, 23(4), 589–609. https://doi.org/10.1111/j.1540-6261.1968.tb00843 |
dc.relation.references | Antonsson, H. (2018). Macroeconomic factors in Probability of Default A study applied to a Swedish credit portfolio [KTH Royal Institute of Technology]. https://www.diva-portal.org/smash/record.jsf?pid=diva2%3A1264976&dswid=3197 |
dc.relation.references | Apergis, E., Apergis, I., & Apergis, N. (2019). A new macro stress testing approach for financial realignment in the Eurozone. Journal of International Financial Markets, Institutions and Money, 61(4), 52–80. https://doi.org/10.1016/j.intfin.2019.02.002 |
dc.relation.references | Banco de la República de Colombia. (2022). Sectorización Monetaria y Económica. https://www.banrep.gov.co/sites/default/files/paginas/sectormon.pdf |
dc.relation.references | Bandyopadhyay, A. (2022). Loan level loss given default (LGD) study of Indian banks. IIMB Management Review, 34(2), 168–177. https://doi.org/10.1016/J.IIMB.2022.06.003 |
dc.relation.references | Banerjee, R., & Venkateshwaran, S. (2017, July). Demystifying Expected Credit Loss (ECL). KPMG. https://assets.kpmg/content/dam/kpmg/in/pdf/2017/07/Demystifying-Expected-Credit-Loss.pdf |
dc.relation.references | Bastos, J. A. (2010). Forecasting bank loans loss-given-default. Journal of Banking & Finance, 34(10), 2510–2517. https://doi.org/10.1016/J.JBANKFIN.2010.04.011 |
dc.relation.references | BCBS. (2000). Principles for the Management of Credit Risk. Basel Committee on Banking Supervision. https://www.bis.org/publ/bcbs75.htm |
dc.relation.references | Bemister-Buffington, J., Wolf, A. J., Raschka, S., & Kuhn, L. A. (2020). Machine Learning to Identify Flexibility Signatures of Class A GPCR Inhibition. Biomolecules, 10(3). https://doi.org/10.3390/biom10030454 |
dc.relation.references | Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324 |
dc.relation.references | Cheng, J., Sun, J., Yao, K., Xu, M., & Cao, Y. (2022). A variable selection method based on mutual information and variance inflation factor. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 268(6), 1–7. https://doi.org/https://doi.org/10.1016/j.saa.2021.120652 |
dc.relation.references | Chen, J. (2022, September 6). Default: What It Means, What Happens When You Default, Examples. Investopedia. https://www.investopedia.com/terms/d/default2.asp |
dc.relation.references | Chen, M. (2011). Bankruptcy prediction in firms with statistical and intelligent techniques and a comparison of evolutionary computation approaches. Computers & Mathematics with Applications, 62(12), 4514–4524. https://doi.org/10.1016/J.CAMWA.2011.10.030 |
dc.relation.references | Chen, T., & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785 |
dc.relation.references | Dupré la Tour, T., Eickenberg, M., Nunez-Elizalde, A. O., & Gallant, J. L. (2022). Feature-space selection with banded ridge regression. NeuroImage, 264(19), 1–19. https://doi.org/10.1016/J.NEUROIMAGE.2022.119728 |
dc.relation.references | ECB. (2023, June 30). What are haircuts? European Central Bank. https://www.ecb.europa.eu/ecb/educational/explainers/tell-me-more/html/haircuts.en.html |
dc.relation.references | Fernando, J. (2023a, March 27). Inventory Turnover Ratio: What It Is, How It Works, and Formula. Investopedia. https://www.investopedia.com/terms/i/inventoryturnover.asp |
dc.relation.references | Fernando, J. (2023b, May 24). Return on Equity (ROE) Calculation and What It Means. Investopedia. https://www.investopedia.com/terms/r/returnonequity.asp |
dc.relation.references | Filippo, M., Alfonso, N., Theodore, P., Enrico, R., & Gerhard, S. (2017). IFRS 9: A silent revolution in banks’ business models. McKinsey. https://www.mckinsey.com/capabilities/risk-and-resilience/our-insights/ifrs-9-a-silent-revolution-in-banks-business-models |
dc.relation.references | Fischler, M. A., & Bolles, R. C. (1981). Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. Commun. ACM, 24(6), 381–395. https://doi.org/10.1145/358669.358692 |
dc.relation.references | Fonti, V., & Belitser, E. (2017). Feature selection using lasso. In VU Amsterdam research paper in business analytics. Vrije Universitetit Amsterdam. |
dc.relation.references | Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5), 1189 – 1232. https://doi.org/10.1214/aos/1013203451 |
dc.relation.references | Genuer, R., Poggi, J. M., & Tuleau-Malot, C. (2010). Variable selection using random forests. Pattern Recognition Letters, 31(14), 2225–2236. https://doi.org/10.1016/J.PATREC.2010.03.014 |
dc.relation.references | Geurts, P., Ernst, D., & Wehenkel, L. (2006). Extremely randomized trees. Machine Learning, 63(1), 3–42. https://doi.org/10.1007/s10994-006-6226-1 |
dc.relation.references | Giesecke, K., Longstaff, F. A., Schaefer, S., & Strebulaev, I. (2011). Corporate bond default risk: A 150-year perspective. Journal of Financial Economics, 102(2), 233–250. https://doi.org/10.1016/J.JFINECO.2011.01.011 |
dc.relation.references | Giraud, C. (2021). Introduction to High-Dimensional Statistics (CRC Press, Ed.; 2nd, illustrated ed.). https://www.imo.universite-paris-saclay.fr/~christophe.giraud/Orsay/Bookv3.pdf |
dc.relation.references | Gitman, L. J., & Zutter, C. J. (2012). Principios de Administración financiera (12th ed.). Pearson Educación de México, S.A. de C.V. https://economicas.unsa.edu.ar/afinan/informacion_general/book/pcipios-adm-finan-12edi-gitman.pdf |
dc.relation.references | Granitto, P. M., Furlanello, C., Biasioli, F., & Gasperi, F. (2006). Recursive feature elimination with random forest for PTR-MS analysis of agroindustrial products. Chemometrics and Intelligent Laboratory Systems, 83(2), 83–90. https://doi.org/10.1016/J.CHEMOLAB.2006.01.007 |
dc.relation.references | Guyon, I., Weston, J., Barnhill, S., & Vapnik, V. (2002). Gene Selection for Cancer Classification using Support Vector Machines. Machine Learning, 46(1), 389–422. https://doi.org/10.1023/A:1012487302797 |
dc.relation.references | Härdle, W. K., & Prastyo, D. D. (2013). Default Risk Calculation based on Predictor Selection for the Southeast Asian Industry. SSRN Electronic Journal, SFB 649(Discussion Paper 2013-037), 1–24. https://doi.org/10.2139/ssrn.2892650 |
dc.relation.references | Hastie, T., Tibshirani, R., & Friedman, J. (2001). The Elements of Statistical Learning (2nd ed.). Springer New York Inc |
dc.relation.references | Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition (Springer Series in Statistics). https://doi.org/10.1007/978-0-387-84858-7 |
dc.relation.references | Hayes, A. (2022, August 10). EBITDA: Meaning, Formula, and History. Investopedia. https://www.investopedia.com/terms/e/ebitda.asp |
dc.relation.references | Heo, J., & Yang, J. Y. (2014). AdaBoost based bankruptcy forecasting of Korean construction companies. Applied Soft Computing, 24(13), 494–499. https://doi.org/10.1016/J.ASOC.2014.08.009 |
dc.relation.references | Hoerl, A. E., & Kennard, R. W. (1970). Ridge Regression: Biased Estimation for Nonorthogonal Problems. Technometrics, 12(1), 55–67. https://doi.org/10.1080/00401706.1970.10488634 |
dc.relation.references | Jiménez, G., & Mencía, J. (2009). Modelling the distribution of credit losses with observable and latent factors. Journal of Empirical Finance, 16(2), 235–253. https://doi.org/10.1016/j.jempfin.2008.10.003 |
dc.relation.references | Kendall, M. G. (1948). Rank correlation methods. In Rank correlation methods. Griffin & Co. https://doi.org/10.1017/S0020268100013019 |
dc.relation.references | Khamis, H. (2008). Measures of Association: How to Choose? Journal of Diagnostic Medical Sonography, 24(3), 155–162. https://doi.org/10.1177/8756479308317006 |
dc.relation.references | Khandani, A. E., Kim, A. J., & Lo, A. W. (2010). Consumer credit-risk models via machine-learning algorithms. Journal of Banking & Finance, 34(11), 2767–2787. https://doi.org/10.1016/J.JBANKFIN.2010.06.001 |
dc.relation.references | Leow, M., & Mues, C. (2012). Predicting loss given default (LGD) for residential mortgage loans: A two-stage model and empirical evidence for UK bank data. International Journal of Forecasting, 28(1), 183–195. https://doi.org/10.1016/J.IJFORECAST.2011.01.010 |
dc.relation.references | Liu, J., & Xu, X. E. (2003). The Predictive Power of Economic Indicators in Consumer Credit Risk Management. The Rma Journal, 86, 40–45. https://acortar.link/7x2mfu |
dc.relation.references | Loh, W.-Y. (2011). Classification and Regression Trees. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 1(1), 14–23. https://doi.org/10.1002/widm.8 |
dc.relation.references | Louppe, G. (2014). Understanding Random Forests: From Theory to Practice [Université de Liège]. https://doi.org/10.48550/arXiv.1407.7502 |
dc.relation.references | Lundberg, S., Erion, G., & Lee, S.-I. (2018). Consistent Individualized Feature Attribution for Tree Ensembles. Arxiv. https://doi.org/10.48550/arXiv.1802.03888 |
dc.relation.references | Lundberg, S., & Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. https://www.researchgate.net/publication/317062430 |
dc.relation.references | Luong, T. M., & Scheule, H. (2022). Benchmarking forecast approaches for mortgage credit risk for forward periods. European Journal of Operational Research, 299(2), 750–767. https://doi.org/10.1016/j.ejor.2021.09.026 |
dc.relation.references | Maulud, D., & Abdulazeez, A. M. (2020). A Review on Linear Regression Comprehensive in Machine Learning. Journal of Applied Science and Technology Trends, 1(4), 140–147. https://doi.org/10.38094/jastt1457 |
dc.relation.references | Mazibaş, M., & Tuna, Y. (2017). Understanding the Recent Growth in Consumer Loans and Credit Cards in Emerging Markets: Evidence from Turkey. Emerging Markets Finance and Trade, 53(10), 2333–2346. https://doi.org/10.1080/1540496X.2016.1196895 |
dc.relation.references | Melkumova, L. E., & Shatskikh, S. Y. (2017). Comparing Ridge and LASSO estimators for data analysis. Procedia Engineering, 201(31), 746–755. https://doi.org/10.1016/J.PROENG.2017.09.615 |
dc.relation.references | Meng, Y., Yang, N., Qian, Z., & Zhang, G. (2021). What Makes an Online Review More Helpful: An Interpretation Framework Using XGBoost and SHAP Values. Journal of Theoretical and Applied Electronic Commerce Research, 16(3), 466–490. https://doi.org/10.3390/jtaer16030029 |
dc.relation.references | Nalluri, M., Pentela, M., & Eluri, N. R. (2020). A Scalable Tree Boosting System: XG Boost. Int. J. Res. Stud. Sci. Eng. Technol, 7(12), 36–51. https://doi.org/10.22259/2349-476X.0712005 |
dc.relation.references | Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, É. (2011). Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12, 2825–2830. http://scikit-learn.sourceforge.net. |
dc.relation.references | Pereira, J. M., Basto, M., & Silva, A. F. da. (2016). The Logistic Lasso and Ridge Regression in Predicting Corporate Failure. Procedia Economics and Finance, 39(5), 634–641. https://doi.org/10.1016/S2212-5671(16)30310-0 |
dc.relation.references | Peterdy, K. (2023, June 14). Credit Risk. CFI. https://corporatefinanceinstitute.com/resources/knowledge/finance/credit-risk |
dc.relation.references | Robles, C. L. (2012). Fundamentos de administración financiera (M. E. Buendía, Ed.; 1st ed.). Red Tercer Milenio S.C. http://biblioteca.udgvirtual.udg.mx/jspui/handle/123456789/3175 |
dc.relation.references | Rory, M., Andrey, A., Thejaswi, R., & Eibe, F. (2018). XGBoost: Scalable GPU Accelerated Learning. Cornell University. https://doi.org/10.48550/arXiv.1806.11248 |
dc.relation.references | Ross, S. A., Westerfiel, R. W., & Jordan, B. D. (2010). Fundamentos de finanzas corporativas (9th ed.). McGraw-Hill/IInteramericana Editores, S.A.de C.V. https://www.mheducation.com.co/fundamentos-de-finanzas-corporativas-9781456291136-col-group |
dc.relation.references | Rubaszek, M., & Serwa, D. (2014). Determinants of credit to households: An approach using the life-cycle model. Economic Systems, 38(4), 572–587. https://doi.org/10.1016/J.ECOSYS.2014.05.004 |
dc.relation.references | Stoppiglia, H., Dreyfus, G., Dubois, R., & Oussar, Y. (2003). Ranking a Random Feature For Variable And Feature Selection. Journal of Machine Learning Research, 3, 1399–1414. https://doi.org/10.1162/153244303322753733 |
dc.relation.references | Taghiyeh, S., Lengacher, D. C., & Handfield, R. B. (2021). Loss rate forecasting framework based on macroeconomic changes: Application to US credit card industry. Expert Systems with Applications, 165(3), 113954. https://doi.org/10.1016/J.ESWA.2020.113954 |
dc.relation.references | Temim, J. (2016, November). The IFRS 9 Impairment Model and its Interaction with the Basel Framework. Moody’s Analytics. Risk Perspectives. https://acortar.link/3HQHP5 |
dc.relation.references | Theil, H. (1949). A Rank-Invariant Method of Linear and Polynomial Regression Analysis. In Advanced Studies in Theoretical and Applied Econometrics (Vol. 23). Springer, Dordrecht. https://doi.org/10.1007/978-94-011-2546-8_20 |
dc.relation.references | Vipond Tim. (2022, June). Net Working Capital. CFI. https://corporatefinanceinstitute.com/resources/knowledge/finance/what-is-net-working-capital/ |
dc.relation.references | Wang, X., Wang, X., Ma, B., Li, Q., Wang, C., & Shi, Y. (2023). High-performance reversible data hiding based on ridge regression prediction algorithm. Signal Processing, 204(3), 108818. https://doi.org/10.1016/J.SIGPRO.2022.108818 |
dc.relation.references | Wang, Y. (2011). Corporate Default Prediction: Models, Drivers and Measurements [Doctoral thesis, University of Exeter]. http://hdl.handle.net/10036/3457 |
dc.relation.references | Xia, Y., Zhao, J., He, L., Li, Y., & Yang, X. (2021). Forecasting loss given default for peer-to-peer loans via heterogeneous stacking ensemble approach.International Journal of Forecasting, 37(4), 1590–1613. https://doi.org/10.1016/J.IJFORECAST.2021.03.002 |
dc.relation.references | Yeh, C. C., Chi, D. J., & Lin, Y. R. (2014). Going-concern prediction using hybrid random forests and rough set approach. Information Sciences, 254(1), 98–110. https://doi.org/10.1016/J.INS.2013.07.011 |
dc.relation.references | Zhang, Y., & Chen, L. (2021). A Study on Forecasting the Default Risk of Bond Based on XGboost Algorithm and Over-Sampling Method. Theoretical Economics Letters, 11(2), 258–267. https://doi.org/10.4236/tel.2021.112019 |
dc.rights.accessrights | info:eu-repo/semantics/openAccess |
dc.subject.lemb | Riesgo (Finanzas) |
dc.subject.lemb | Bank Loans |
dc.subject.lemb | Préstamos bancarios |
dc.subject.proposal | Pérdida crediticia esperada |
dc.subject.proposal | Provisión |
dc.subject.proposal | Entidades financieras |
dc.subject.proposal | Riesgo de default |
dc.subject.proposal | Extremely Randomized Trees |
dc.subject.proposal | Extra Trees |
dc.subject.proposal | Expected Credit Loss |
dc.subject.proposal | ECL |
dc.subject.proposal | Provision |
dc.subject.proposal | Financial institutions |
dc.subject.proposal | Default risk |
dc.subject.proposal | Default |
dc.title.translated | Forecasting expected credit loss of high-risk bank clients using parametric and non-parametric models |
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 |
dc.type.redcol | http://purl.org/redcol/resource_type/TM |
oaire.accessrights | http://purl.org/coar/access_right/c_abf2 |
dcterms.audience.professionaldevelopment | Estudiantes |
dcterms.audience.professionaldevelopment | Investigadores |
dcterms.audience.professionaldevelopment | Maestros |
dc.description.curriculararea | Área Curricular Estadística |
dc.contributor.orcid | González Álvarez, Nelfi Gertrudis [0000-0003-0129-1316] |
dc.contributor.cvlac | González Álvarez, Nelfi Gertrudis [0000063002] |
Archivos en el documento
Este documento aparece en la(s) siguiente(s) colección(ones)
Esta obra está bajo licencia internacional Creative Commons Reconocimiento-NoComercial 4.0.Este documento ha sido depositado por parte de el(los) autor(es) bajo la siguiente constancia de depósito