Modelo sencillo para la predicción de la calificación crediticia para empresas fintech aplicando técnicas SMOTE y MRMR

Barra lateral del artículo

The Anáhuac Journal
PDF (English) XML (English)
Publicado: Dec 2, 2024
DOI: https://doi.org/10.36105/theanahuacjour.2024v24n2.2516
Palabras clave:
FinTech, Calificación Crediticia, SMOTE, MRMR, Aprendizaje Automático

Contenido principal del artículo

Jesús Gopar Sánchez
EGADE Business School, Tecnológico de Monterrey, Mexico
https://orcid.org/0000-0002-5616-3066

Resumen

Las empresas fintech han mejorado la eficiencia de la industria financiera y han umentado la inclusión financiera. Sin embargo, también han incorporado nuevos riesgos al sistema financiero. Los reguladores, los inversionistas y los investigadores están preocupados de que sus dificultades financieras puedan afectar a todo el sistema financiero. Nuestro estudio tiene como objetivo profundizar en la eficacia de las técnicas de machine learning (aprendizaje automático) para identificar alertas tempranas de deterioro del riesgo crediticio de las fintech. Valiéndonos de medidas contables y de mercado comúnmente empleadas en la literatura, creamos varios clasificadores para predecir las calificaciones crediticias de las fintech. Los algoritmos de clasificación enfrentan un desafío cuando el número de observaciones entre clases no es equivalente, lo que afecta su desempeño. Debido al tamaño limitado de las fintech que cotizan en la bolsa y que tienen una calificación crediticia a nivel de emisor, nuestra base de datos incluye pocas observaciones y está muy desequilibrada. Los resultados de nuestro estudio muestran que la técnica de sobremuestreo SMOTE mejora el poder predictivo de los algoritmos de aprendizaje automático y que los algoritmos de selección de características como MRMR permiten la generación de modelos más sencillos y fáciles de entender. Nuestros resultados sugieren que los algoritmos de clasificación basados en KNN tienen mayor precisión para predecir las calificaciones crediticias de las fintech.

Descargas

Los datos de descargas todavía no están disponibles.

PLUMX Metrics

Detalles del artículo

Cómo citar
Gopar Sánchez, J. (2024). Modelo sencillo para la predicción de la calificación crediticia para empresas fintech aplicando técnicas SMOTE y MRMR. The Anáhuac Journal, 24(2), Pág. 1–29. https://doi.org/10.36105/theanahuacjour.2024v24n2.2516
Número
Vol. 24 Núm. 2 (2024): The Anáhuac Journal, Vol. 24, núm. 2, 2024, Segundo Semestre
Sección
Artículos
Creative Commons License

Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.

The Anáhuac Journal se distribuye bajo Licencia Creative Commons Atribución-NoComercial-CompartirIgual 4.0 Internacional.

 

Biografía del autor/a

Jesús Gopar Sánchez, EGADE Business School, Tecnológico de Monterrey, Mexico

Jesús began his professional career in the financial sector in 1998. For ten years, he held various positions related to credit analysis and investment project evaluation in commercial and development banking. He served as the Director of Transactional Advisory Services at Salles Sainz Grant Thornton, S.C. Since 2015, he has been a partner responsible for the valuation, mergers, and acquisitions practice at Liberty Analysis, S.C. Jesús has provided advisory services to publicly traded and private companies across various industries, focusing on valuation, mergers and acquisitions, strategy, financing, recovery, reorganization, and operational optimization. He has conducted various seminars at the Mexican Institute for Finance Executives (IMEF). He has been a professor for the bachelor’s degree in economics courses at Universidad Anáhuac and the Master’s Degree in Finance at UNAM. He is a professor in the Department of Accounting and Finance at TEC de Monterrey. Jesús has a bachelor’s degree in Economics and an MBA in Finance from TEC de Monterrey. He is currently a PhD in Financial Science candidate at TEC de Monterrey.

Citas

Agarwal, S., & Zhang, J. (2020). FinTech, Lending and Payment Innovation: A Review. Asia-Pacific Journal of Financial Studies, 49(3), 353–367. https://doi.org/10.1111/ajfs.12294

Al-Shari, H. A., & Lokhande, M. A. (2023). The Relationship Between the Risks of Adopting FinTech in Banks and their Impact on the Performance. Cogent Business and Management, 10(1). https://doi.org/10.1080/23311975.2023.2174242

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/10.2307/2978933

Anagnostopoulos, I. (2018). Fintech and Regtech: Impact on Regulators and Banks. Journal of Economics and Business, 100, 7–25. https://doi.org/10.1016/j.jeconbus.2018.07.003

Bellotti, T., & Crook, J. (2009). Support vector machines for credit scoring and discovery of significant features. Expert Systems with Applications, 36(2), 3302–3308. https://doi.org/10.1016/j.eswa.2008.01.005

Beneish, M. D. (1999). The Detection of Earnings Manipulation. Financial Analysts Journal, 55(5), 24–36. http://www.jstor.org/stable/4480190

Bloomberg. (2024). Country Risk Premium. Retrieved on June 13, 2024, Bloomberg Professional (database).

Brownlee, J. (2021). Imbalanced Classification with Python: Better Metrics, Balance Skewed Classes, and Apply Cost-Sensitive Learning. Self-published.

Cevik, S. (2024) The Dark Side of the Moon? Fintech and Financial Stability. International Review of Economics, 71, 421–433. https://doi.org/10.1007/s12232-024-00449-8

Chaudhry, S. M., Ahmed, R., Huynh, T. L. D., & Benjasak, C. (2022). Tail Risk and Systemic Risk of Finance and Technology (FinTech) Firms. Technological Forecasting and Social Change, 174, 121191. https://doi.org/10.1016/j.techfore.2021.121191

Chawla, N. v, Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic Minority Over-Sampling Technique. Journal of Artificial Intelligence Research, 16, 321–357. https://doi.org/10.1613/jair.953

Dastile, X., Celik, T., & Potsane, M. (2020). Statistical and Machine Learning Models in Credit Scoring: A Systematic Literature Survey. Applied Soft Computing Journal, 91, 106263. https://doi.org/10.1016/j.asoc.2020.106263

Demirgüç-Kunt, A., Klapper,L., Singer, D., Ansar, S. 2022. The Global Findex Database 2021: Financial Inclusion, Digital Payments, and Resilience in the Age of COVID-19. World Bank. https://doi.org/10.48529/jq97-aj70

Ding, C., & Peng, H. (2005). Minimum Redundancy Feature Selection from Microarray Gene Expression Data. Journal of Bioinformatics and Computational Biology, 3(2), 185–205. https://doi.org/10.1142/s0219720005001004

Doumpos, M., Niklis, D., Zopounidis, C., & Andriosopoulos, K. (2015). Combining Accounting Data and a Structural Model for Predicting Credit Ratings: Empirical Evidence from European Listed Firms. Journal of Banking and Finance, 50, 599–607. https://doi.org/10.1016/j.jbankfin.2014.01.010

Durand, D. (1941). Risk Elements in Consumer Installment Financing. National Bureau of Economy Research (NBER). https://econpapers.repec.org/bookchap/nbrnberbk/dura41-1.htm

Friedman, J. H. (1991). Multivariate Adaptive Regression Splines. The Annals of Statistics, 19(1), 1–67. https://www.jstor.org/stable/2241837

Galil, K., Hauptman, A., & Rosenboim, R. L. (2023). Prediction of Corporate Credit Ratings with Machine Learning: Simple Interpretative Models. Finance Research Letters, 58, 104648. https://doi.org/10.1016/j.frl.2023.104648

Golbayani, P., Florescu, I., & Chatterjee, R. (2020). A Comparative Study of Forecasting Corporate Credit Ratings Using Neural Networks, Support Vector Machines, and Decision Trees. North American Journal of Economics and Finance, 54, 101251. https://doi.org/10.1016/j.najef.2020.101251

Gupton, G. M., Finger, C.C., & Bhatia, M. (1997). CreditMetrics™: Technical Document. J.P. Morgan & Company Incorporated. https://www.researchgate.net/publication/301776007_CreditMetrics_-_Technical_Document

Hajek, P., & Michalak, K. (2013). Feature Selection In Corporate Credit Rating Prediction. Knowledge-Based Systems, 51, 72–84. https://doi.org/10.1016/j.knosys.2013.07.008

Henrique, B. M., Sobreiro, V. A., & Kimura, H. (2019). Literature Review: Machine Learning Techniques Applied to Financial Market Prediction. Expert Systems with Applications, 124, 226–251. https://doi.org/10.1016/j.eswa.2019.01.012

Li, J. P., Mirza, N., Rahat, B., & Xiong, D. (2020). Machine Learning and Credit Ratings Prediction in the Age of Fourth Industrial Revolution. Technological Forecasting and Social Change, 161, 120309. https://doi.org/10.1016/j.techfore.2020.120309

Jiang, Y. (2022). Credit Ratings, Financial Ratios, and Equity Risk: A Decomposition Analysis Based on Moody’s, Standard & Poor’s and Fitch’s ratings. Finance Research Letters, 46, 102512. https://doi.org/10.1016/j.frl.2021.102512

Junarsin, E., Pelawi, R. Y., Kristanto, J., Marcelin, I., & Pelawi, J. B. (2023). Does Fintech Lending Expansion Disturb Financial System Stability? Evidence from Indonesia. Heliyon, 9(9), e18384. https://doi.org/10.1016/j.heliyon.2023.e18384

Kealhofer, S., McQuown, J., & Vasicek, O. (1997). The KMV Model for Credit Portfolio Management. KMV Corporation.

Kiff, J., Kisser, M., & Schumacher, L. (2013). Rating Through-the-Cycle: What Does the Concept Imply for Rating Stability and Accuracy? IMF Working Paper 13(64). https://doi.org/10.5089/9781475552119.001

Merton, R.C. (1974). On The Pricing Of Corporate Debt: The Risk Structure Of Interest Rates. The Journal of Finance, 29(2). 449-470. https://doi.org/10.1111/j.1540-6261.1974.tb03058.x

Metz, A. & Cantor, R. (2006). The Distribution of Common Financial Ratios by Rating and Industry for North American Non-Financial Corporations: July 2006, Moody’s Special Comment. (Report Number: 98551). https://www.moodys.com/sites/products/defaultresearch/2005700000436062.pdf

Milian, E. Z., Spinola, M. de M., & Carvalho, M. M. de. (2019). Fintechs: A Literature Review and Research Agenda. Electronic Commerce Research and Applications, 34, 100833. https://doi.org/10.1016/j.elerap.2019.100833

Siriseriwan, W. (2021). Smotefamily: A Collection of Oversampling Techniques for Class Imbalance Problem Based on SMOTE. [R package smotefamily version 1.4.0]. https://CRAN.R-project.org/package=smotefamily

Snoek, J., Larochelle, H., & Adams, R P. (2012). Practical Bayesian Optimization of Machine Learning Algorithms. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1206.2944

Sundar, R., & Punniyamoorthy, M. (2019). Performance Enhanced Boosted SVM for Imbalanced Datasets. Applied Soft Computing Journal, 83, 105601. https://doi.org/10.1016/j.asoc.2019.105601

Statista. (2023). Transaction Value of Fintech Industry Worldwide from 2018 to 2023, with Forecasts from 2024 to 2028, by Segment (in Trillion U.S. dollars). Statista Digital Market Insights. Retrieved June 30, 2024. https://www.statista.com/statistics/1384088/estimated-global-fintech-transaction-value-by-segment/

Statista. (2024a). Number of Fintech Users Worldwide from 2023 to 2023, with Forecasts from 2024 to 2028, by Segment (in Billions). Statista Digital Market Insights. Retrieved June 27, 2024. https://www.statista.com/statistics/1384328/estimated-fintech-users-by-segment/

Statista. (2024b). Number of Fintechs Worldwide from 2018 to 2024, by Region. Statista. Retrieved June 27, 2024. https://www.statista.com/statistics/893954/number-fintech-startups-by-region/

S&P Global (2024). Understanding Credit Ratings. https://www.spglobal.com/ratings/en/about/intro-to-credit-ratings

S&P Capital IQ. (2024). Payment Processors; Payment Service Providers and Gateways; Mobile Wallets; Payments Fraud Management; Money Transfer and Remittance; Payments Infrastructure: Public company profile. Retrieved on June 13, 2024 (database).

Tello-Gamarra, J., Campos-Teixeira, D., Longaray, A. A., Reis, J., & Hernani-Merino, M. (2022). Fintechs and Institutions: A Systematic Literature Review and Future Research Agenda. Journal of Theoretical and Applied Electronic Commerce Research, 17(2), 722-750. https://doi.org/10.3390/jtaer17020038

Treu, J., Elss, V. I., Buono, G., & Winkler, P. (2021). The Rising of Fintech–How the Tech Revolution in Financial Services Represents a Paradigm Shift. Journal of International Business and Management, 4(5), 1-8. https://doi.org/10.37227/JIBM-2021-03-718

Wilson, T. C. (1998). Portfolio Credit Risk. Economic Policy Review, Vol. 4, No. 3. http://dx.doi.org/10.2139/ssrn.1028756