Credit Default Risk Analysis Using Machine Learning Algorithms with Hyperparameter Optimization

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

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.

Original languageEnglish
Title of host publicationIntelligent Technologies
Subtitle of host publicationDesign and Applications for Society - Proceedings of CITIS 2022
EditorsVladimir Robles-Bykbaev, Josefa Mula, Gilberto Reynoso-Meza
PublisherSpringer Science and Business Media Deutschland GmbH
Pages81-95
Number of pages15
ISBN (Print)9783031243264
DOIs
StatePublished - 2023
Event8th International Conference on Science, Technology and Innovation for Society, CITIS 2022 - Guayaquil, Ecuador
Duration: 22 Jun 202224 Jun 2022

Publication series

NameLecture Notes in Networks and Systems
Volume607 LNNS

Conference

Conference8th International Conference on Science, Technology and Innovation for Society, CITIS 2022
Country/TerritoryEcuador
CityGuayaquil
Period22/06/2224/06/22

Bibliographical note

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

Keywords

  • Binary classification
  • Credit risk
  • Gradient boosting
  • Machine learning

Fingerprint

Dive into the research topics of 'Credit Default Risk Analysis Using Machine Learning Algorithms with Hyperparameter Optimization'. Together they form a unique fingerprint.

Cite this