Credit Default Risk Analysis Using Machine Learning Algorithms with Hyperparameter Optimization

Producción científica: Capítulo del libro/informe/acta de congresoContribución de conferenciarevisión exhaustiva

2 Citas (Scopus)

Resumen

Machine learning models are an important tool that provide a scientific method to identify potential debtors early and predict which clients are more likely to default on their debts, improving the accuracy of assessment in credit risk analysis in financial companies. The purpose of this study was to analyze the performance of gradient boosting machine learning algorithms (CatBoost, LightGBM, and XGBoost) in predicting customer default risk, and the ability of the RandomUnderSampler sampling technique to address unbalanced categories of credit risk. The exploratory analysis of the data set was carried out, then the data preprocessing, finally the training with hyperparameter adjustments with the GridSearchCV method to identify the largest number of clients with credit risk. The model is evaluated based on metrics of sensitivity, specificity and precision, on a set of consumer credit data. Among the proposed algorithms, XGBoost outperformed the LightGBM and catBoost models. Experimental results confirmed that the XGBoost model performs better for credit risk prediction with historical data.

Idioma originalInglés
Título de la publicación alojadaIntelligent Technologies
Subtítulo de la publicación alojadaDesign and Applications for Society - Proceedings of CITIS 2022
EditoresVladimir Robles-Bykbaev, Josefa Mula, Gilberto Reynoso-Meza
EditorialSpringer Science and Business Media Deutschland GmbH
Páginas81-95
Número de páginas15
ISBN (versión impresa)9783031243264
DOI
EstadoPublicada - 2023
Evento8th International Conference on Science, Technology and Innovation for Society, CITIS 2022 - Guayaquil, Ecuador
Duración: 22 jun. 202224 jun. 2022

Serie de la publicación

NombreLecture Notes in Networks and Systems
Volumen607 LNNS

Conferencia

Conferencia8th International Conference on Science, Technology and Innovation for Society, CITIS 2022
País/TerritorioEcuador
CiudadGuayaquil
Período22/06/2224/06/22

Nota bibliográfica

Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Huella

Profundice en los temas de investigación de 'Credit Default Risk Analysis Using Machine Learning Algorithms with Hyperparameter Optimization'. En conjunto forman una huella única.

Citar esto