Unleashing Predicting a Comparative Study of Machine Learning for Bankruptcy Risk Prediction

In the dynamic landscape of financial risk management, accurately predicting banks' susceptibility to bankruptcy is deemed a critical imperative. Predictive analytics are advanced through the utilization of sophisticated machine learning methodologies, specifically the Random Forest classificat...

Full description

Saved in:
Bibliographic Details
Main Authors: Yupeng Li, Ke Sun
Format: Article
Language:English
Published: Bilijipub publisher 2024-03-01
Series:Journal of Artificial Intelligence and System Modelling
Subjects:
Online Access:https://jaism.bilijipub.com/article_193320_992713a8dfcb5042cdd01e83a191879a.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849404753876877312
author Yupeng Li
Ke Sun
author_facet Yupeng Li
Ke Sun
author_sort Yupeng Li
collection DOAJ
description In the dynamic landscape of financial risk management, accurately predicting banks' susceptibility to bankruptcy is deemed a critical imperative. Predictive analytics are advanced through the utilization of sophisticated machine learning methodologies, specifically the Random Forest classification model (RFC), The Grasshopper Optimizer Algorithm (GOA), and the Artificial Rabbits Optimizer (ARO). The intricate interplay of these techniques aims to enhance the precision and efficacy of bankruptcy prediction models. Traditional methodologies often fall short of capturing the complexity of contemporary financial landscapes. Machine learning provides an avenue to address this challenge, simultaneously allowing for a nuanced analysis of various factors. This research responds to the existing literature gap by employing data mining techniques for automated knowledge extraction from financial databases and emphasizing a pioneering approach grounded in the qualitative domain. Specifically, superior performance is exhibited by the combined model, denoted as RFAR, with an accuracy of 0.972, in stark contrast to the RFGO model, which achieves an accuracy of 0.956, and the RFC model, identified as the weakest among these models, with an accuracy of 0.930. This notable difference underscores the effectiveness of integrating machine learning methodologies, particularly the RFC model, GOA, and ARO, in predicting the likelihood of banks going bankrupt.
format Article
id doaj-art-6ab6142ef5a44e49804b960dea6f5b77
institution Kabale University
issn 3041-850X
language English
publishDate 2024-03-01
publisher Bilijipub publisher
record_format Article
series Journal of Artificial Intelligence and System Modelling
spelling doaj-art-6ab6142ef5a44e49804b960dea6f5b772025-08-20T03:36:53ZengBilijipub publisherJournal of Artificial Intelligence and System Modelling3041-850X2024-03-0102019911310.22034/jaism.2024.445968.1029193320Unleashing Predicting a Comparative Study of Machine Learning for Bankruptcy Risk PredictionYupeng Li0Ke Sun1School of Accountancy Anyang Institute of Technology, 455000, Henan, ChinaUBS Business Solutions (China) Co. Ltd Wuxi Branch, Wuxi, Jiangsu, 214000, ChinaIn the dynamic landscape of financial risk management, accurately predicting banks' susceptibility to bankruptcy is deemed a critical imperative. Predictive analytics are advanced through the utilization of sophisticated machine learning methodologies, specifically the Random Forest classification model (RFC), The Grasshopper Optimizer Algorithm (GOA), and the Artificial Rabbits Optimizer (ARO). The intricate interplay of these techniques aims to enhance the precision and efficacy of bankruptcy prediction models. Traditional methodologies often fall short of capturing the complexity of contemporary financial landscapes. Machine learning provides an avenue to address this challenge, simultaneously allowing for a nuanced analysis of various factors. This research responds to the existing literature gap by employing data mining techniques for automated knowledge extraction from financial databases and emphasizing a pioneering approach grounded in the qualitative domain. Specifically, superior performance is exhibited by the combined model, denoted as RFAR, with an accuracy of 0.972, in stark contrast to the RFGO model, which achieves an accuracy of 0.956, and the RFC model, identified as the weakest among these models, with an accuracy of 0.930. This notable difference underscores the effectiveness of integrating machine learning methodologies, particularly the RFC model, GOA, and ARO, in predicting the likelihood of banks going bankrupt.https://jaism.bilijipub.com/article_193320_992713a8dfcb5042cdd01e83a191879a.pdfartificial rabbits optimizerrandom forest classification modelgrasshopper optimizer algorithmmachine learningbankruptcy
spellingShingle Yupeng Li
Ke Sun
Unleashing Predicting a Comparative Study of Machine Learning for Bankruptcy Risk Prediction
Journal of Artificial Intelligence and System Modelling
artificial rabbits optimizer
random forest classification model
grasshopper optimizer algorithm
machine learning
bankruptcy
title Unleashing Predicting a Comparative Study of Machine Learning for Bankruptcy Risk Prediction
title_full Unleashing Predicting a Comparative Study of Machine Learning for Bankruptcy Risk Prediction
title_fullStr Unleashing Predicting a Comparative Study of Machine Learning for Bankruptcy Risk Prediction
title_full_unstemmed Unleashing Predicting a Comparative Study of Machine Learning for Bankruptcy Risk Prediction
title_short Unleashing Predicting a Comparative Study of Machine Learning for Bankruptcy Risk Prediction
title_sort unleashing predicting a comparative study of machine learning for bankruptcy risk prediction
topic artificial rabbits optimizer
random forest classification model
grasshopper optimizer algorithm
machine learning
bankruptcy
url https://jaism.bilijipub.com/article_193320_992713a8dfcb5042cdd01e83a191879a.pdf
work_keys_str_mv AT yupengli unleashingpredictingacomparativestudyofmachinelearningforbankruptcyriskprediction
AT kesun unleashingpredictingacomparativestudyofmachinelearningforbankruptcyriskprediction