Publicación:
Predicción de quiebras empresariales en turismo colombiano mediante k-NN funcional y una métrica de distancia personalizada (1995–2023)

dc.contributor.advisorPorras Gómez, Hernando
dc.contributor.authorRuiz Paredes, Luis Eduardo
dc.contributor.juryCosio Borda, Ricardo Fernando
dc.contributor.juryOrtiz Ruiz, Emanuel Elberto
dc.contributor.juryCano Blandón, Rodolfo León
dc.contributor.researchgroupEMPRENDIMIENTO Y GERENCIA::GRUPO DE GERENCIA EN LAS GRANDES, MEDIANA Y PEQUEÑAS EMPRESAS G3PYMES OMAR ALONSO PATIÑO CASTRO Categoría A1 COL0016327
dc.creator.id1032410362
dc.date.accessioned2025-11-23T22:48:39Z
dc.date.issued2025-11-05
dc.description.abstractEsta investigación doctoral desarrolla como aporte metodológico original una métrica funcional multivariada personalizada para comparar trayectorias financieras multivariadas de empresas. Esta métrica permite evaluar la similitud entre entidades a partir de la evolución de sus indicadores financieros durante cinco años, incluso en presencia de datos faltantes o escalas heterogéneas. Al integrarse en un clasificador k-vecinos más cercanos (k-NN), el modelo resultante ofrece un equilibrio entre rendimiento predictivo e interpretabilidad, permitiendo visualizar y analizar los vecinos más cercanos en el espacio funcional. Para su validación empírica, se aplicó la metodología al problema de predicción de quiebra en empresas del sector turismo en Colombia, un segmento estratégico para la economía nacional que ha mostrado alta vulnerabilidad ante crisis financieras y operativas. Se construyó una base longitudinal con más de 5.000 empresas (1995–2023) y se identificaron eventos de quiebra mediante criterios financieros y operativos. A pesar del auge reciente de técnicas de aprendizaje automático aplicadas a este problema, persisten limitaciones clave: muchos modelos avanzados operan como “cajas negras” difíciles de interpretar, no permiten visualizar la similitud concreta entre empresas y tienden a ignorar la estructura dinámica de las trayectorias financieras multivariadas. El modelo funcional fue evaluado con validación cruzada estratificada, alcanzando un F1-score promedio de 0,9802, una sensibilidad del 96,35% y una precisión del 99,76%, resultados que lo posicionan como una alternativa competitiva frente a modelos más complejos como XGBoost, redes LSTM o arquitecturas hibridas. Si bien no supera a todos en desempeño, su principal fortaleza radica en la posibilidad de identificar empresas similares (vecinas) de manera explicita y explicar la relevancia de cada indicador mediante los pesos optimizados en la métrica, lo que lo convierte en un complemento valioso para sistemas de alerta temprana y análisis financiero. Además del desarrollo metodológico, se construyó un aplicativo computacional interactivo que permite estimar el riesgo de quiebra de una empresa y mostrar sus vecinos financieros más cercanos en función de la métrica propuesta. Esta herramienta refuerza la aplicabilidad del modelo al proporcionar trazabilidad, explicaciones claras y posibilidades reales de uso por parte de analistas, supervisores o gestores no técnicos. La hipótesis de este trabajo plantea que un modelo k-NN funcional basado en una métrica de distancia personalizada, diseñada para trayectorias financieras multivariadas, puede alcanzar un desempeño competitivo frente a modelos avanzados, manteniendo interpretabilidad y capacidad de visualización de similitudes.spa
dc.description.abstractThis doctoral research proposes an original methodological contribution: a custom multivariate functional distance metric for comparing financial trajectories of firms. This metric allows assessing the similarity between entities based on the evolution of their financial indicators over five years, even in the presence of missing data or heterogeneous scales. When integrated into a k-nearest neighbors (k-NN) classifier, the resulting model offers a balance between predictive performance and interpretability, enabling the visualization and analysis of nearest neighbors in the functional space. For empirical validation, the methodology was applied to the problem of bankruptcy prediction in firms from Colombia’s tourism sector, a strategic segment for the national economy that has shown high vulnerability to financial and operational crises. A longitudinal database of over 5,000 firms (1995–2023) was built, identifying bankruptcy events through financial and operational criteria. Despite the recent surge of machine learning techniques applied to this problem, key limitations persist: many advanced models operate as black boxes, are difficult to interpret, do not allow for concrete similarity visualizations, and often ignore the dynamic structure of multivariate financial trajectories. The functional model was evaluated through stratified cross-validation, achieving an average F1-score of 0.9802, a sensitivity of 96.35%, and a precision of 99.76%. These results position it as a competitive alternative to more complex models like XGBoost, LSTM networks, or hybrid architectures. While it does not outperform all others in accuracy, its main strength lies in the explicit identification of similar (neighboring) firms and the explanation of each indicator’s relevance through optimized weights in the metric. This makes it a valuable complement to early warning systems and financial analysis tools. In addition to the methodological development, an interactive web application was built. It allows users to estimate a firm’s bankruptcy risk and display its closest financial neighbors according to the proposed metric. This tool reinforces the model’s applicability by providing traceability, clear explanations, and real usability for analysts, supervisors, or non-technical managers. The hypothesis of this study posits that a functional k-NN model based on a custom distance metric tailored for multivariate financial trajectories can achieve competitive performance compared to advanced models while maintaining interpretability and the ability to visualize similarities.eng
dc.description.degreelevelDoctoradospa
dc.description.degreenameDoctor en Gestiónspa
dc.description.researchareaEMPRENDIMIENTO Y GERENCIA::GRUPO DE GERENCIA EN LAS GRANDES, MEDIANA Y PEQUEÑAS EMPRESAS G3PYMES OMAR ALONSO PATIÑO CASTRO Categoría A1 COL0016327::Contaduría, finanzas y negocios internacionales para las organizaciones
dc.description.tableofcontentsÍndice general Resumen Abstract 1. Contextualización 1.1. Introducción 1.2. Planteamiento del problema 1.3. Justificación 1.4. Pregunta de investigación 1.5. Objetivos 1.6. Hipótesis 1.7. Delimitación de la investigación 2. Marco teórico y estado del arte en la predicción del riesgo empresarial 2.1. Fundamentos metodológicos de los modelos de aprendizaje automático para predicción de quiebra 2.2. Estado del arte 3. Marco metodológico: diseño del modelo funcional y métrica personalizada 3.1. Construcción del Espacio Funcional 3.2. Definición de la métrica funcional personalizada 3.3. Discretización de la métrica funcional para implementación práctica 3.3.1. Ejemplo ilustrativo del cálculo de la métrica funcional 3.4. Extensiones posibles de la métrica funcional personalizada 3.4.1. Extensión 1: Incorporación de variables categóricas estáticas 3.4.2. Extensión 2: Incorporación de variables categóricas dinámicas 3.4.3. Extensión 3: Incorporación de variables cuantitativas estáticas 4. Procesamiento de datos, imputación contable y generación de variables predictoras 4.1. Fuentes de información y cobertura temporal 4.1.1. Imputación contable estructurada de cuentas financieras 4.1.2. Imputación técnica de cuentas financieras 4.2. Cálculo, imputación y estructuración de indicadores financieros 4.3. Construcción de la variable dependiente (riesgo de quiebra) 4.4. Análisis exploratorio multivariado: colinealidad y estructura latente 4.4.1. Exploración de estructura latente mediante PCA 5. Evaluación empírica del modelo funcional 5.1. Modelo funcional para comparación con enfoques tradicionales 5.1.1. Optimización de hiperparámetros y pesos por indicador 5.1.2. Evaluación del modelo funcional base con parámetros óptimos 5.1.3. Robustez del modelo 5.1.4. Análisis aplicado del modelo funcional 5.1.5. Importancia relativa de los indicadores financieros 5.2. Versión final del modelo funcional con variables categóricas y temporales 5.2.1. Redefinición de la métrica con variables categóricas y temporales 5.2.2. Optimización de parámetros del modelo final 5.2.3. Evaluación del modelo funcional extendido 5.3. Reproducibilidad del modelo funcional y disponibilidad del código 5.4. Aplicación interactiva del modelo funcional en entorno web 6. Comparación de modelos predictivos 6.1. Metodología comparativa 6.2. Resultados comparativos por tipo de modelo 6.2.1. Modelos tradicionales estáticos 6.2.2. Modelos k-NN funcionales con métricas estándar 6.2.3. Modelos avanzados basados en árboles de decisión 6.2.4. Modelos secuenciales 6.2.5. Modelos híbridos 6.3. Síntesis comparativa y discusión final 6.4. Reproducibilidad de los modelos comparativos 7. Conclusiones 7.1. Cumplimiento de los objetivos 7.2. Aportes al conocimiento y a la práctica 7.2.1. Comparación con la literatura reciente 7.3. Limitaciones y proyecciones futuras 7.4. Conclusión General
dc.formatpdf
dc.format.extent192 páginas
dc.format.mediumRecurso electrónicospa
dc.format.mimetypeapplication/pdf
dc.identifier.instnameinstname:Universidad Eanspa
dc.identifier.localBDM-DG
dc.identifier.reponamereponame:Repositorio Institucional Minervaspa
dc.identifier.repourlrepourl:https://repository.universidadean.edu.co/
dc.identifier.urihttps://hdl.handle.net/10882/15404
dc.language.isospa
dc.publisher.facultyFacultad de Administración, Finanzas y Ciencias Económicas
dc.publisher.placeBogotá, Colombia
dc.publisher.programDoctorado en Gestiónspa
dc.relation.references• Abrahamsen, N. - G. B., Nylen-Forthun, E., Moller, M., de Lange, P. E., & Risstad, M. (2024). Financial Distress Prediction in the Nordics: Early Warnings from Machine Learning Mo dels [Op en Access un- der CC BY 4.0]. Journal of Risk and Financial Management , 17 (10), 432. https://doi.org/10.3390/jrfm17100432 • Alaka, H. A., Oyedele, L. O., Owolabi, H. A., Kumar, V., Ajayi, S. O., Akinade, O. O., & Bilal, M. (2018). Systematic review of bankruptcy prediction mo dels: Towards a framework for to ol selection. Expert Systems with Applications , 94 , 164 - 184. https://doi.org/10.1016/j.eswa.2017.10.040 • Alam, N., Gao, J., & Jones, S. (2021). Corp orate failure prediction: An evaluation of deep learning vs discrete hazard mo dels. Journal of International Financial Markets, Institutions & Money , 75 , 101455. https://doi.org/10.1016/j.intn.2021.101455 • Alamari, M. B., Almulhim, F. A., Kaid, Z., & Laksaci, A. (2024). k-Nearest Neighb ors Estimator for Functional Asymmetry Shortfall Regression. Symmetry , 16 (7), 928. https://doi.org/10.3390/sym16070928 • Aljawazneh, H., Mora, A., Garca-Sanchez, P., & Castillo, P. (2021). Compa- ring the Performance of Deep Learning Metho ds to Predict Companies' Financial Failure. IEEE Access . https : / / doi . org / 10 . 1109 / ACCESS . 2021.3093461 • Almanjahie, I. M., Bouzeb da, S., Kaid, Z., & Laksaci, A. (2024). The lo cal linear functional kNN estimator of the conditional exp ectile: uniform consistency in numb er of neighb ors. Metrika , 87 , 1 - 27. https : / / doi . org/10.1007/s00184- 023- 00942- 0 • Altman, E. I. (1968). Financial Ratios, Discriminant Analysis and the Predic- tion of Corp orate Bankruptcy. The Journal of Finance , 23 (4), 589 - 609. • Amer, A. A., Ravana, S. D., & Habeeb, R. A. A. (2025). Eectivek-nearest neighbor models for data classication enhancement. Journal of Big Data , 12 (86). https://doi.org/10.1186/s40537- 025- 01137- 2 • Amirshahi, B., & Lahmiri, S. (2024). Bankruptcy prediction using optimal ensemble mo dels under balanced and imbalanced data. Expert Systems , 41 (8), e13599. https://doi.org/10.1111/exsy.13599 • Ansah-Narh, B., Yang, C. - H., & Lin, C. - W. (2024). Enhancing corp orate bankruptcy prediction via a hybrid genetic algorithm and domain adaptation learning architecture. Expert Systems with Applications , 235 , 121289. https://doi.org/10.1016/j.eswa.2023.121289 • Ansari, A., Ahmad, I. S., Abu Bakar, A., & Yaakub, M. R. (2020). A Hy- brid Metaheuristic Metho d in Training Articial Neural Network for Bankruptcy Prediction. IEEE Access , 8 , 176640 - 176650. https : //doi.org/10.1109/ACCESS.2020.3026529 • Antulov-Fantulin, N., Lagravinese, R., & Resce, G. (2021). Predicting ban- kruptcy of local government: A machine learning approach. Jour- nal of Economic Behavior and Organization , 183 , 681 - 699. https : //doi.org/10.1016/j.jeb o.2021.01.014 • Antunes, F., Ribeiro, B., & Pereira, F. (2017). Probabilistic modeling and visualization for bankruptcy prediction. Applied Soft Computing , 60 , 831-843. https://doi.org/10.1016/j.aso c.2017.06.043 • Baíllo, A., Cuevas, A., & Cuesta-Albertos, J. A. (2011). Supervised Classi- cation for a Family of Gaus sian Functional Mo dels. Scandinavian Journal of Statistics , 38 (3), 480 - 498. https://doi. org/10.1111/j.1467- 9469.2011.00734.x • Barboza, F., & Altman, E. (2024). Predicting nancial distress in Latin American companies: A comparative analysis of logistic regression and random forest mo dels. North American Journal of Economics and Finance , 72 , 102158. https://doi.org/10.1016/j.na jef.2024.102158 • Barboza, F., Cruz Basso, L. F., & Kimura, H. (2021). New metrics and approaches for predicting bankruptcy. Communications in Statistics - Simulation and Computation , 2615 - 2632. https : / / doi . org / 10 . 1080 / 03610918.2021.1910837 • Barboza, F., Kimura, H., & Altman, E. (2017). Machine learning models and bankruptcy prediction. Expert Systems with Applications , 83 , 405 - 417. https://doi.org/10.1016/j.eswa.2017.04.006 • Bargagli-Stoffi, F. J., Incerti, F., Riccab oni, M., & Rungi, A. (2023). Machine Learning for Zombie Hunting: Predicting Distress from Firms' Accounts and Missing Values [arXiv preprint]. https://arxiv.org/abs/2306.08165 • Ben Jabeur, S., Gharib, C., Mefteh-Wali, S., & Ben Ar, W. (2021). Cat- Bo ost mo del and articial intelligence techniques for corp orate failure prediction. Technological Forecasting and Social Change , 166 , 120658. https://doi.org/10.1016/j.techfore.2021.120658 • Borges, A., & Carvalho, M. (2025). Short- and long-term nancial distress prediction in SMEs: a survival mo del comparison [Sp ecial Issue: Compu- tational Data Analys is and Numerical Metho ds (WCDANM 2024), Published online: 16 May 2025]. Journal of Applied Statistics . https: //doi.org/10.1080/02664763.2025.2501166 • Campbell, J. Y., Hilscher, J., & Szilagyi, J. (2008). In search of distress risk. The Journal of Finance , 63 (6), 2899-2939. • Carmona, M., Climent, F., & Momparler, A. (2019). Predicting failure in the US banking sector: an extreme gradient b o osting approach. Interna- tional Review of Economics & Finance , 61 , 304 - 320. https://doi.org/ 10.1016/j.iref.2018.03.008 • Carmona, P., Dwekat, A., & Mardawi, Z. (2022). No more black b oxes! Explaining the predictions of a machine learning XGBo ost classier algorithm in business failure. Research in Internati onal Business and Finance , 61 , 101649. https://doi.org/10.1016/j.ribaf.2022.101649 • Chen, M. G. (2023). Estimating Sparsely and Irregularly Observed Multi- variate Functional Data. The ITEA Journal of Test and Evaluation , 44 (3). https://doi.org/10.61278/itea.44.3.1009 • Chen, T., & Guestrin, C. (2016). XGBo ost: A Scalable Tree Bo osting System. Proceedings of the 22nd ACM SIGKDD International Conference on Know ledge Discovery and Data Mining , 785 - 794. https : // doi. org /10 . 1145/2939672.2939785 • Chen, W., et al. (2025). Multi-class nancial distress prediction based on hybrid feature selection and improved stacking ensemble mo del. Expert Systems with Applications . • Chen, W. - C., Chen, L. - C., Wang, C. - H., & Lee, C. - F. (2020). Ensemble learning with lab el prop ortions for bankruptcy prediction. Information Sciences , 516 , 108-121. • Chen, X., Liu, J., & Wu, C. (2025). Multi-class Financial Distress Prediction Based on Hybrid Feature Selection and Improved Stacking Ensemble Mo del. Expert Systems with Applications , 282 , 127832. https : / / doi . org/10.1016/j.eswa.2025.127832 • Cheraghali, M., & Molnar, J. (2024). SME default prediction: A systema- tic metho dology-fo cused review. Journal of Business Research , 170 , 114199. https://doi.org/10.1080/00472778.2023.2277426 • Chi, D. - J., & Shen, Z. - D. (2022). Using Hybrid Articial Intelligence and Machine Learning Technologies for Sustainability in Going-Concern Prediction. Sustainability , 14 (3), 1810. https : / / doi . org / 10 . 3390 / su14031810 • Climent, F., Momparler, A., & Carmona, M. (2019). Anticipating bank distress in the Eurozone: An Extreme Gradient Bo osting approach. Journal of Financial Stability , 40 , 100693. https://doi.org/10.1016/j.jbusres.2018. 11.015 • Correa, A. (2023). Predicting Business Bankruptcy in Colombian SMEs: A Machine Learning Approach. Journal of International Commerce, Economics an d Policy , 14 (4), 2350027. https : / / doi . org / 10 . 1142 / S1793993323500278 • Dasilas, A., & Rigani, A. (2024). Machine learning techniques in bankruptcy prediction: A systematic literature review. Expert Systems with Appli- cations , 255 , 124761. https://doi.org/10.1016/j.eswa.2024.124761 • du Jardin, P. (2016). A two-stage classication technique for bankruptcy prediction. European Journal of Operational Research , 254 , 236 - 252. https://doi.org/10.1016/j.ejor.2016.03.008 • Erdogan, B. (2012). Prediction of bankruptcy using supp ort vector machines. International Journal of Co mputational Economics and Econometrics , 2 (3), 241-252. • Feng, M., Shaonan, T., Lee, C., & Ma, L. (2019). Deep Learning Mo dels for Bankruptcy Prediction Using Textual Disclosures. European Journal of Operational Research , 274 (2), 743 - 758. https://doi.org/10.1016/j. ejor.2018.10.024 • Franco, O. J., Perez, L., & Moreno, C. (2022). Análisis bibliométrico de la literatura sobre quiebra empresarial con enfoque en inteligencia artificial y aprendiza je automático. Revista Colombiana de Ciencias Administrativas, 40 (2), 21-45. • Galeano, P., et al. (2015). Mahalanobis distance for functional data with applications. Wiley Interdisciplinary Reviews: Computational Statistics . • Gnip, P., Kanasz, R., Zoricak, M., & Drotar, P. (2025). An Exp erimental Survey of Imbalanced Learning Algorithms for Bankruptcy Prediction. Articial Intel ligence Review , 58 , 104. https://doi.org/10.1007/s10462- 025- 11107- y • Guenani, S., Bouabsa, W., Fetitah, O., Kadi Attouch, M., & Khardani, S. (2024). Some Asymptotic Results of a kNN Conditional Mo de Estimator for Functional Stationary Ergo dic Data. Communications in Statistics - Theory and Methods . https : // doi .org / 10 .1080 / 03610926. 2024.2384557 • Guenani, S., Bouabsa, W., Kadi Attouch, M., & Fetitah, O. (2023). kNN Robustication Equivariant Nonparametric Regression Estimators for Functional Ergo dic Data. Hacettepe Journal of Mathematics and Statistics , 52 (2), 512-528. https://doi.org/10.15672/hujms.1100871 • Guerra, P., & Castelli, M. (2021). Machine Learning Applied to Banking Sup ervision: A Literature Review. Risks , 9 (7), 136. https://doi.org/ 10.3390/risks9070136 Ho chreiter, S., & Schmidhub er, J. (1997). Long short-term memory. Neural Computation , 9 (8), 1735 - 1780. https://doi.org/10.1162/neco.1997.9.8. 1735 • Horvathova, J., & Mokrisova, M. (2018). Risk of Bankruptcy, Its Determinants and Mo dels [Op en access under CC BY 4.0 license]. Risks , 6 (4), 117. https://doi.org/10.3390/risks6040117 • Hosaka, T. (2019). Bankruptcy prediction using imaged nancial ratios and convolutional neural networks. Expert Systems with Applications , 117 , 287-299. https://doi.org/10.1016/j.es wa.2018.09.039 • Hu, W. (2022). k-NN nonparametric regression for negatively asso ciated data with applications to bankruptcy prediction. Journal of Computational and Applied Mathematics , 400 , 113747. https : // doi .org / 10. 1016 /j . cam. 2021.113747 • Hu, X., Wang, J., Wang, L., & Yu, K. (2022). K-Nearest Neighb or Estimation of Functional Nonparametric Regression Mo del under NA Samples. Axioms , 11 (3), 102. https://doi.org/10.3390/axioms11030102 • Huang, Y. - P., & Yen, M. - F. (2019). A New Persp ective of Performance Com- parison Among Machine Learning Algorithms for Financial Distress Prediction. Applied Soft Computing , 83 , 105663. https : / / doi . org / 10 . 1016/j.aso c.2019.105663 • Iparraguirre, J. A., Reinoso, D., & Pérez, M. (2024). Predicting business bankruptcy: A comparative analysis with machine learning mo dels. Expert Systems with Applications , 235 , 121419. https : / / doi . org / 10 . 1016/j.eswa.2023.121419 • Issa, S., Bizel, G., Jagannathan, S. K., & Gollapalli, S. S. C. (2024). A Com- prehensive Approach to Bankruptcy Risk Evaluation in the Financial Industry [Op en access under CC BY 4.0 license]. Journal of Risk and Fi- nancial Management , 17 (1), 41. https://doi.org/10.3390/jrfm17010041 • James, G., Witten, D., Hastie, T., & Tibshirani, R. (2021). An Introduction to Statistical Learning: with Applications in R (2nd). Springer. • James, N., Menzies , M., & Chan, J. (2023). Semi-Metric Portfolio Optimiza- tion: A New A lgorithm Reducing Simultaneous Asset Sho cks. Econo- metrics , 11 (1), 8. https://doi.org/10.3390/econometrics11010008 • Ji, H., Zhao, R., & Zhang, P. (2025). A dynamic nancial risk prediction system for enterprises based on gradient b o osting decision tree algorithm. Expert Systems with Applications , 231 , 120609. https : / / doi . org / 10 . 1016/j.eswa.2023.120609 • Kar, A. K., Akhter, M. M., Mishra, A. C., & Mohanty, S. K. (2024). EDMD: An Entropy based Dis similarity measure to cluster Mixed-categorical Data. Pattern Recognition , 155 , 110674. https : / / doi . org / 10 . 1016 / j . patcog.2024.110674 • Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T. - Y. (2017). LightGBM: A Highly Ecient Gradient Bo osting Decision Tree. Advances in Neural Information Processing Systems 30 (NeurIPS 20 17) , 3146 - 3154. https://pap ers.nips.cc/pap er les/pap er/ 2017/le/6449f44a102fde848669b dd9eb6b76fa- Paper.pdf • Kim, S. - H., Lee, J. - Y., & Kim, Y. - K. (2022). Bankruptcy prediction using temp oral data with long short-term memory mo dels. Mathematics , 10 (9), 1345. • Kuizinien _e, D., Krilavicius, T., Damasevicius, R., & Maskeliunas, R. (2022). Systematic Review of Financial Distress Identication us ing Articial Intelligence Metho ds. Applied Ar ticial Intel ligence , 36 (1), 2138124. https://doi.org/10.1080/08839514.2022.2138124 • Kutner, M. H ., Nachtsheim, C. J., & Neter, J. (2005). Applied Linear Regres- sion Models (4th). McGraw-Hill/Irwin. • Lin, F., Yeh, C. - C., & Lee, M. - Y. (2011). The Us e of Hybrid Manifold Learning and Supp ort Vector Machines in the Prediction of Business Failure. Know ledge-Based Systems , 24 (1), 95 - 101. https: // doi. org/ 10. 1016/ j. knosys.2010.07.009 • Lin, Y. - M., & Chang, P. - Y. (2023). Bankruptcy prediction using convolutional neural networks and SHAP interpretability. Know ledge-Based Systems , 258 , 110033. https://doi.org/10.1016/j.knosys.2022.110033 • Liu, P., Yuan, H., Ning, Y., et al. (2024). A mo died and weighted Gower distance-based clustering analysis for mixed typ e data: a simulation and empirical analyses. BMC Medical Research Methodology , 24 (1), 305. https://doi.org/10.1186/s12874- 024- 02427- 8 • Liu, Y., Chen, H., & Zhang, W. (2025). Financial distress prediction with annual rep orts-based deep textual feature extraction: A hybrid ap- proach. Information Processing & Management , 62 (2), 103574. https: //doi.org/10.1016/j.ipm.2024.103574 • Lundb erg, S., & Lee, S. - I. (2017). A Unied Approach to Interpreting Mo del Predictions [To app ear in NeurIPS 2017]. arXiv preprint ar- Xiv:1705.07874 . https://doi.org/10.48550/arXiv.1705.07874 • M., A ., R. M., A. S., T. N., D., S., M. S., & J., V. (2025). Predicting Bankruptcy With Precision: Insights From Hybrid Machine Learning Mo dels On Unbalanced Polis h Financial Data. International Journal for Scientic Research and Technology (IJSART) , 11 (5), 57 - 65. https: //ijsart.com/public/storage/pap er/p df/IJSARTV11I5103465.pdf • Marso, K., Malebary, S. J., & Belkacem, S. (2020). Bankruptcy prediction using hybrid neural networks with articial b ee colony. Computational Intel ligence and Neuroscience . • Muslim, M. A., & Yosza, D. (2021). Company bankruptcy prediction fra- mework based on the most influential features using XGBo ost and stacking ensemble learning. International Journal of Electrical and Computer Engineering , 11 (6), 5549 - 5557. https://doi.org/10.11591/ijece.v11i6.pp5549- 5557 • Nagendrakumar, N., Alwis, K. N. N., Eshani, U . A. K., & Kaushalya, S. B. U. (2023). Prediction of Corp orate Financial Distress in the Travel and Tourism Industry [Op en access under CC BY 4.0 license]. Corporate Ownership & Control , 20 (3 (Sp ecial I ssue)), 262 - 267. https://doi.org/ 10.22495/co cv20i3siart2 • Nayak, S. M., & Rout, M. (2023). A predictive mo del for bankruptcy: ANN, LSTM and CNN approaches. Journal of Statisti cs and Management Systems , 26 (1), 67-86. https://doi.org/10.47974/JSMS- 948 • Nazareth, D. L., & Reddy, R. (2023). Applications of Machine and Deep Lear- ning in Finance: A Systematic Review. Applied Articial Intel ligence , 37 (1), 2162678. https://doi.org/10.1016/j.eswa.2023.119640 • Searcoid, M. (2007). Metric Spaces . Springer. • Odom, M. D., & Sharda, R. (1990). A neural network mo del for bankruptcy prediction. Proceedings of the International Joint Conference on Neural Networks , 163-168. • Ohlson, J. A. (1980). Financial ratios and the probabilistic prediction of bankruptcy. Journal of Accounting Research , 109-131. • Papík, M., & Papkova, L. (2024a). Automated Machine Learning in Ban- kruptcy Prediction of Manufacturing Companies. Procedia Computer Science , 232 , 1428-1436. https://doi.org/10.1016/j.pro cs.2024.01.141 • Papík, M., & Papkova, L. (2024b). Automated Machine Learning in Ban- kruptcy Prediction of Manufacturing Companies. Procedia Computer Science , 232 , 1428-1436. https://doi.org/10.1016/j.pro cs.2024.01.141 • Papík, M., Papkova, L., Ka janova, J., & Becka, M. (2022). CatBo ost: The case of bankruptcy prediction. En Sustainable Finance, Digitalization and the Role of Technology (pp. 3 - 17, Vol. 487). Springer. https ://doi.org/10.1007/978-3-031-08084-5_3 • Park, S., Kim, D. - S., & Kim, S. J. (2021). Explainability of Machine Learning Mo dels for Bankruptcy Prediction. Journal of Risk and Financial Management , 14 (12), 535. • Pellegrino, A., Ruiz, D., & Conti, M. (2024). Multi-head LSTM architecture for corp orate bankruptcy prediction [In press]. Journal of Forecasting . • Qian, H., Wang, B., Yuan, M., Gao, S., & Song, Y. (2022). Financial Distress Prediction Using a Corrected Feature Selection Measure and Gradient Bo osted Decision Tree. Expert Systems with Applications , 190 , 116202. https://doi.org/10.1016/j.eswa.2021.116202 • Qu, Y., Quan, P., Lei, M., & Shi, Y. (2019). Review of bankruptcy prediction using machine learning and deep learning techniques. Procedia Compu- ter Science , 162 , 895 - 899. https://doi.org/10.1016/j.pro cs.2019.12.065 • Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). \Why Should I Trust You?": Explaining the Predictions of Any Classier. arXiv preprint arXiv:1602.04938 . https://doi.org/10.48550/arXiv.1602.04938 • Romero Espinosa, F., Melgarejo Molina, Z. A., & Vera-Colina, M. A. (2015). Fracaso empresarial de las pequeñas y medianas empres as (pymes) en Colombia. SUMA de Negocios , 6 (13), 29 - 41. https: / /doi .org / 10. 1016/ j.sumneg.2015.08.003 • Rudin, W. (1976). Principles of Mathematical Analysis (3rd). McGraw-Hill. • Santiago, K., Yanes, A., & Mercado-Caruso, N. (2024). Analyzing Correlations in Sustainable Tourism Perception: Statistical Insights from Diverse Caribb ean Colombian Tourist Sites. Procedia Computer Science , 231 , 490-495. https://doi.org/10.1016/j.pro cs.2023.12.239 • Shetty, S., Musa, M., & Bredart, X. (2022). Bankruptcy Prediction Using Ma- chine Learning Techniques. Journal of Risk and Financial Management , 15 (1), 35. https://doi.org/10.3390/jrfm15010035 • Shi, Y., & Li, X. (2019). A bibliometric study on intelligent techniques of bankruptcy prediction for corp orate rms. Heliyon , 5 (7), e02997. https://doi.org/10.1016/j.heliyon.2019.e02997 • Shumway, T. (2001). Forecasting bankruptcy more accurately: A simple hazard mo del. The journal of business , 74 (1), 101-124. • Son, H., Hyun, C., Phan, D., & Hwang, H. (2019). Data Analytic Approach for Bankruptcy Prediction. Expert Systems with Applications , 138 , 112816. https://doi.org/10.1016/j.eswa.2019.07.033 • Song, Y., Chiangpradit, M., & Busabab o dhin, P. (2025). Hyp erband-Optimized CNN-BiLSTM with Attention Mechanism for Corporate Financial Dis- tress Prediction. Applied Sciences , 15 (11), 5934. https:// doi.org/ 10. 3390/app15115934 • Superintendencia de Sociedades. (2023, marzo). Informe Económico-Financiero del Sector Turismo 2019{2021 [Elaborado por el Grupo de Estudios Empresariales. Bogotá, Colombia.]. • Tellez, J., Hernandez, M., & Murcia, M. P. (2024, octubre). Colombia: Situación Turismo [Fecha de cierre: 18 de octubre de 2024]. https://www.bbvaresearch.com/publicaciones/colombia- situación- turismo- noviembre- 2024/ • Thompson, J. R., & Davison, M. (2024). Functional Mixed-type Clustering of Investors' Daily Returns During a Market Sho ck Change-p oint and Recovery. Proceedings of the 5th ACM International Conference on AI in Finance (ICAIF '24) . https://doi.org/10.1145/3677052.3698633 • Tian, X., & Yu, J. (2012). Recent advances on supp ort vector machines research. Neurocomputing , 74 (1-3), 1-6. • Tsai, C. - F., Hsu, Y. - F., Yen, D. C., & Hsu, C. - C. (2014). A comparative study of classier ensembles for bankruptcy prediction. Applied Soft Computing , 24 , 977-984. • Tserng, H. - C., Lin, C. - Y., & Chen, P. - H. (2011). An enforced supp ort vector machine mo del for construction contractor default prediction. Auto- mation in Construction , 20 (8), 1242-1249. • Vallarino, D. (2024). A Comparative Machine Learning Survival Mo dels Analysis for Predicting Time to Bank Failure in the US (2001{2023) [Op en access under CC BY 4.0 license]. Journal of Economic Analysis , 3 (1), 129-144. https://doi.org/10.58567/jea03010007 • Wang, G., Ma, J., Xu, Y., & Wang, H. (2014). An improved b o osting based on feature selection for corporate bankruptcy prediction. Computers & Industrial Engineering , 74 , 50-61. • Wang, J. - L., Chiou, J. - M., & Muller, H. - G. (2016). Functional Data Analysis. Annual Review of Statistics and Its Application , 3 , 257 - 295. https : //doi.org/10.1146/annurev- statistics- 041715- 033624 • Wang, S., & Chi, G. (2024). Cost-sensitive stacking ensemble learning for com- pany nancial distress prediction. Expert Systems with Applications , 255 (Part A), 124525. https://doi.org/10.1016/j.eswa.2024.124525 • Wang, X., & Brorsson, M. (2024). Augmenting Bankruptcy Prediction Using Rep orted Behavior of Corp orate Restructuring. International Confe- rence on Information and Communication Technology (IC 2023) , 2036 , 1-20. https://doi.org/10.1007/978- 981- 97- 0065- 3 8 • Wilson, R. L., & Sharda, R. (1994). A comparison of neural network and logis- tic regression predictions. Decision Support Systems , 11 (5), 545-557. • Yousaf, U. B., Jebran, K., & Wang, M. (2022). A Comparison of Static, Dynamic and Machine Learning Mo dels in Predicting the Financial Distress of Chinese Firms. Romanian Journal of Economic Forecasting , 25 (1), 122-138. • Zapata, A., & Mukhopadhyay, S. (2024). Evaluation of Hybrid Mo dels for Bankruptcy Prediction [Citado en 2024 SME default prediction A systematic m ethodology-focused review ]. En SME Default Prediction: A Systematic Methodology-Focused Review . Springer. • Zelenkov, Y., Fedorova, E., & Chekrizov, D. (2017). Two-step clas sication metho d based on genetic algorithm for bankruptcy forecasting. Expert Systems with Ap plicatio ns , 88 , 393 - 401. https : / / doi . org / 10 . 1016 / j . eswa.2017.07.025 • Zhang, H., Zhang, Q., & Li, Y. (2016). A nonlinear subspace multiple kernel learning for nancial distress prediction of Chinese listed companies. Know ledge-Based Systems , 94 , 102-111. • Zhang, H., & Zhang, W. (2025). Advancing enterprise risk management with deep learning: A predictive approach using the XGBo ost-CNN- BiLSTM mo del. PLOS ONE , 20 (4), e0319773. https : / / doi . org / 10 . 1371/journal.p one.0319773 • Zhao, J., Ouenniche, J., & De Smedt, J. (2024a). A complex network analysis approach to bankruptcy prediction using company relational information-based drivers. Know ledge-Based Systems , 300 , 112234. https : / / doi . org/10.1016/j.knosys.2024.112234 • Zhao, J., Ouenniche, J., & De Smedt, J. (2024b). Survey, classication and critical analysis of the literature on corp orate bankruptcy and nancial distress prediction. Machine Learning with Applications , 15 , 100527. https://doi.org/10.1016/j.mlwa.2024.100527 • Zieba, M., Tomczak, S. K., & Tomczak, J. M. (2016). Ensemble b o osted trees with synthetic features generation in application to bankruptcy prediction. Expert Systems with Applications , 58 , 93 - 101. https:/ /doi. org/10.1016/j.eswa.2016.04.001
dc.rights.accessrightsinfo:eu-repo/semantics/openAccess
dc.rights.coarhttp://purl.org/coar/access_right/c_abf2
dc.rights.creativecommonsAtribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0)
dc.rights.licenseAtribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0)
dc.rights.localAbierto (Texto Completo)spa
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject.armarcQuiebraspa
dc.subject.armarcFracaso en los negociosspa
dc.subject.armarcTurismo -- Aspectos económicosspa
dc.subject.armarcPronóstico de los negociosspa
dc.subject.armarcCrisis en los negociosspa
dc.subject.lembFracasos comercialesspa
dc.subject.proposalQuiebras empresarialesspa
dc.subject.proposalPredicción de quiebrasspa
dc.subject.proposalSector turismospa
dc.subject.proposalAnálisis funcional de datosspa
dc.subject.proposalTrayectorias multivariadasspa
dc.subject.proposalMétrica de distancia personalizadaspa
dc.subject.proposalClasificación funcional kNNspa
dc.subject.proposalModelos predictivos de riesgospa
dc.subject.proposalBusiness bankruptcyeng
dc.subject.proposalBankruptcy predictioneng
dc.subject.proposalTourism sectoreng
dc.subject.proposalFunctional data analysiseng
dc.subject.proposalMultivariate trajectorieseng
dc.subject.proposalPersonalized distance metriceng
dc.subject.proposalFunctional kNN classificationeng
dc.subject.proposalPredictive risk modelseng
dc.titlePredicción de quiebras empresariales en turismo colombiano mediante k-NN funcional y una métrica de distancia personalizada (1995–2023)spa
dc.titleA custom functional distance metric and k-NN classifier for business bankruptcy prediction in Colombia’s tourism sector (1995–2023)eng
dc.typeTrabajo de grado - Doctoradospa
dc.type.coarhttp://purl.org/coar/resource_type/c_db06
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.contentText
dc.type.driverinfo:eu-repo/semantics/doctoralThesis
dc.type.otherTrabajo de grado - Doctorado
dc.type.redcolhttp://purl.org/redcol/resource_type/TD
dc.type.versioninfo:eu-repo/semantics/acceptedVersion
dspace.entity.typePublication
person.affiliation.nameDoctorado en Gestión

Archivos

Bloque original

Mostrando 1 - 2 de 2
Cargando...
Miniatura
Nombre:
RuizLuis2025.pdf
Tamaño:
5.48 MB
Formato:
Adobe Portable Document Format
Descripción:
Tesis de Doctorado
Cargando...
Miniatura
Nombre:
RuisLuis2025_Anexo.pdf
Tamaño:
183.49 KB
Formato:
Adobe Portable Document Format
Descripción:
Autorización Publicación

Bloque de licencias

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
license.txt
Tamaño:
1.92 KB
Formato:
Item-specific license agreed upon to submission
Descripción: