Fuzzy logic model to evaluate loans in financial entities

Authors

  • Robert Sanchez Programa de Doctorado en Ciencias e Ingeniería. Facultad de Ingeniería, Universidad Nacional de Trujillo, Av. Juan Pablo II s/n – Ciudad Universitaria, Trujillo, Perú. https://orcid.org/0000-0001-9387-1945

DOI:

https://doi.org/10.17268/rev.cyt.2024.04.08

Keywords:

diffusi logic, personal loan, credit risk

Abstract

Financial institutions have a large amount of information about how clients act and their credit history. This data in its raw form is not useful for making correct decisions, requiring an accurate system to differentiate between solvent clients and those at risk. of non-payment. The purpose of this research was to create a fuzzy logic model to minimize credit risk in personal loans in financial institutions. A base set of basic fuzzy rules was designed to provide a framework in which expert knowledge and data can be used for risk modeling. The study was carried out using a pre-experimental design, with an evaluation before and after the intervention in a single group. A sample of 358 clients was used, extracted from a population of 5,000 clients from a dataset provided by the Kaggle platform. In this research, a personal loan application evaluation model was developed that uses fuzzy logic using Python to serve as decision support to determine the creditworthiness of the applicants. The model was validated in terms of accuracy and efficiency.

References

Arutjothi, G., & Senthamarai, C. (2023). Credit Risk Analysis Using Fuzzy Logic with Machine Learning Models. International Journal for Multidisciplinary Research (IJFMR), V(3), 1-7. doi:https://doi.org/10.36948/ijfmr.2023.v05i03.3298

Bennouna, G., & Tkiouat, M. (2018). Fuzzy logic approach applied to credit scoring for microfinance in Morocco. Procedia Computer Science, CXXVII, 274-283. doi:10.1016/j.procs.2018.01.123

Blahun, I. S., Blahun, I. I., & Blahun, S. I. (2020). Assessing the stability of the banking system based on fuzzy logic methods. Banks and Bank Systems, XV(3), 171-183. doi:http://dx.doi.org/10.21511/bbs.15(3).2020.15

Brkic, S., Hodzic, M., & Dzanic, E. (2017). Fuzzy Logic Model of Soft Data Analysis for Corporate Client Credit Risk Assessment in Commercial Banking. Fifth Scientific Conference with International Participation “Economy of Integration” ICEI 2017, (págs. 1-10). Tuzla· Bosnia and Herzegovina. Obtenido de https://ssrn.com/abstract=3079471

Díaz Córdova, J. F., Cobá Molina, E., & Navarrete López, P. (2017). Fuzzy logic and financial risk. A proposed classification. Contaduría y Administración, LXII(5), 1687-1703. doi:https://doi.org/10.1016/j.cya.2017.10.001

Ginting, S., Risman, M. R., Ginting, Y., & Skom, S. (2020). The Application of Fuzzy Logic Method in the Debtors Eligibility Assessment System of Microfinance Institution. IOP Conference Series: Materials Science and Engineering, DCCCLXXIX, págs. 1-8. doi:0.1088/1757-899X/879/1/012039

Ikuomola, A. J., & Falade, F. V. (2020). DEVELOPMENT OF FUZZY EXPERT DECISION SUPPORT SYSTEM FOR MORTGAGE. African Journal of Science & Nature, XI, 13-22. Obtenido de https://journals.oouagoiwoye.edu.ng/v2/index.php/AJSN/article/view/303

Kaggle. (2022). Kaggle. Obtenido de https://www.kaggle.com/datasets/luisenriquesguerrero/creditos-personales-actualizado

Kin, T. Y., Aizam, A. H., Hasan, S. A., Ariffin, A. F., & Mahat, N. (2021). Bankruptcy Prediction Model with Risk Factors using Fuzzy Logic Approach. Journal of Computing Research and Innovation (JCRINN), VI(2), 102-110. doi:https://doi.org/10.24191/jcrinn.v6i2.220

Latinovic, M., Dragovic, I., Arsic, V., & Petrovic, B. (2018). A Fuzzy Inference System for Credit Scoring using Boolean Consistent Fuzzy Logic. International Journal of Computational Intelligence Systems, XI(1), 411427. doi:10.2991/ijcis.11.1.31

Maraj, E., & Kuka, S. (2019). Credit Risk Assessment using Fuzzy Logic. Journal of Multidisciplinary Engineering Science and Technology (JMEST), VI(6), 10239-10242. Obtenido de https://www.jmest.org/wp-content/uploads/JMESTN42352980.pdf

Medina, S., & Paniagua, G. (2008). Modelo de inferencia difuso para estudio de crédito. Dyna, LXXV (154), 215-229. doi:https://doi.org/10.5709/ce.1897-9254.270. Obtenido de http://www.redalyc.org/articulo.oa?id=49615421

Paganoti Fonseca, D., Fernandes Wanke, P., & Correa, H. L. (2020). A two-stage fuzzy neural approach for credit risk assessment in a. Applied Soft Computing Journal, XCII, 1-12. doi:https://doi.org/10.1016/j.asoc.2020.106329

Palamarchuk, O. (2020). THE USE OF FUZZY LOGIC WHILE MODELING THE CREDITWORTHINESS OF LEGAL ENTITIES. Green, Blue & Digital Economy Journal, I(2), 57-61. doi:https://doi.org/10.30525/2661-5169/2020-2-11

Saeed, S. K., & Hagras, H. (2019). A Fraud-Detection Fuzzy Logic Based System for the Sudanese Financial Sector. SUST Journal of Engineering and Computer Science (JECS),, XX(1), 17-30. Obtenido de https://core.ac.uk/download/pdf/323246006.pdf

Salih, A., & Hagras, H. (2018). Towards a Type-2 Fuzzy Logic Based System for Decision Support to Minimize Financial Default in Banking Sector. 10th Computer Science and Electronic Engineering (CEEC),, (págs. 46-49). Colchester, UK. doi:10.1109/CEEC.2018.8674212

Soto, Ana. (2004). Desarrollo de un sistema de inferencia difuso para la evaluación de crédito por parte de una empresa prestadora de servicios. Dyna, LXXI (143), 25-36. doi:https://doi.org/10.5709/ce.1897-9254.270. Obtenido de http://www.redalyc.org/articulo.oa?id=49614303

Tomasz, K. (2018). The implementation of fuzzy logic in forecasting financial ratios. Contemporary Economics, XII(2), 165-188. doi:https://doi.org/10.5709/ce.1897-9254.270

Downloads

Published

2024-12-28

How to Cite

Sanchez, R. . (2024). Fuzzy logic model to evaluate loans in financial entities. Revista CIENCIA Y TECNOLOGÍA, 20(4), 99-119. https://doi.org/10.17268/rev.cyt.2024.04.08

Issue

Vol. 20 No. 4 (2024): Octubre -Diciembre

Section

Artículos Originales

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Los autores/as que publiquen en esta revista aceptan las siguientes condiciones:

  1. Los autores/as conservan los derechos de autor y ceden a la revista el derecho de la primera publicación, con el trabajo registrado con la licencia de atribución de Creative Commons, que permite a terceros utilizar lo publicado siempre que mencionen la autoría del trabajo y a la primera publicación en esta revista.

  2. Los autores/as pueden realizar otros acuerdos contractuales independientes y adicionales para la distribución no exclusiva de la versión del artículo publicado en esta revista (p. ej., incluirlo en un repositorio institucional o publicarlo en un libro) siempre que indiquen claramente que el trabajo se publicó por primera vez en esta revista.

  3. Se permite y recomienda a los autores/as a publicar su trabajo en Internet (por ejemplo en páginas institucionales o personales) antes y durante el proceso de revisión y publicación, ya que puede conducir a intercambios productivos y a una mayor y más rápida difusión del trabajo publicado