Comprehensive Evaluation of Bankruptcy Prediction in Taiwanese Firms Using Multiple Machine Learning Models

Bankruptcy prediction is a significant issue in finance because accurate predictions would enable stakeholders to act quickly to reduce their financial losses. This study developed an advanced bankruptcy prediction model using Support Vector Machines (SVM), Random Forest (RF), and Artificial Neural...

Full description

Saved in:
Bibliographic Details
Main Authors: Hung V. Pham, Tuan Chu, Tuan M. Le, Hieu M. Tran, Huong T.K. Tran, Khanh N. Yen, Son V. T. Dao
Format: Article
Language:English
Published: Universitas Indonesia 2025-01-01
Series:International Journal of Technology
Subjects:
Online Access:https://ijtech.eng.ui.ac.id/article/view/7227
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832576007169638400
author Hung V. Pham
Tuan Chu
Tuan M. Le
Hieu M. Tran
Huong T.K. Tran
Khanh N. Yen
Son V. T. Dao
author_facet Hung V. Pham
Tuan Chu
Tuan M. Le
Hieu M. Tran
Huong T.K. Tran
Khanh N. Yen
Son V. T. Dao
author_sort Hung V. Pham
collection DOAJ
description Bankruptcy prediction is a significant issue in finance because accurate predictions would enable stakeholders to act quickly to reduce their financial losses. This study developed an advanced bankruptcy prediction model using Support Vector Machines (SVM), Random Forest (RF), and Artificial Neural Network (ANN) algorithms based on datasets from the UCI machine learning repository. The core contribution of this research is the establishment of a hybrid model that effectively combines multiple machine learning (ML) algorithms with advanced data with the Synthetic minority oversampling technique Tomek (SMOTE Tomek) or SMOTE- Edited Nearest Neighbor (SMOTE-ENN) resampling data technique to improve bankruptcy prediction accuracy. Additionally, a wrapper-based feature selection (FS) utilizing Binary Particle Swarm Optimization (BPSO) was utilized to find an optimal feature subset and boost the model’s predictive performance. After selecting the best features, these were used to train the three ML algorithms, and hyper-parameter optimization was implemented to boost model performance. From the results measured by evaluation metrics, the proposed model ANN with the combination of parameter tuning, feature selection algorithm, SMOTE-ENN, and optimal hyper-parameters demonstrates superior performance compared to traditional methods, achieving an F1 Score of 98.5% and an accuracy of 98.6%. The results suggest that the predictive performance of bankruptcy models can be significantly enhanced by integrating multiple analytical methodologies.  This approach not only improves the accuracy but also the reliability of financial risk assessments, providing valuable insights for investors, financial analysts, and policymakers. The success of the model opens avenues for further research into hybrid predictive models in various sectors of finance, potentially transforming risk assessment methodologies.
format Article
id doaj-art-a42d455743854942a5c90e4ca570d654
institution Kabale University
issn 2086-9614
2087-2100
language English
publishDate 2025-01-01
publisher Universitas Indonesia
record_format Article
series International Journal of Technology
spelling doaj-art-a42d455743854942a5c90e4ca570d6542025-01-31T14:13:03ZengUniversitas IndonesiaInternational Journal of Technology2086-96142087-21002025-01-0116128930910.14716/ijtech.v16i1.72277227Comprehensive Evaluation of Bankruptcy Prediction in Taiwanese Firms Using Multiple Machine Learning ModelsHung V. Pham0Tuan Chu1Tuan M. Le2Hieu M. Tran3Huong T.K. Tran4Khanh N. Yen5Son V. T. Dao6School of Science, Engineering and Technology, RMIT University Vietnam, 700000, Ho Chi Minh City, VietnamSchool of Science, Engineering and Technology, RMIT University Vietnam, 700000, Ho Chi Minh City, VietnamSchool of Science, Engineering and Technology, RMIT University Vietnam, 700000, Ho Chi Minh City, VietnamSchool of Science, Engineering and Technology, RMIT University Vietnam, 700000, Ho Chi Minh City, VietnamSchool of Industrial Engineering and Management, International University, Vietnam National University Ho Chi Minh City, 700000, HCMC, VietnamInternational University, Vietnam National University Ho Chi Minh City, 700000,HCMC, VietnamSchool of Science, Engineering and Technology, RMIT University Vietnam, 700000, Ho Chi Minh City, VietnamBankruptcy prediction is a significant issue in finance because accurate predictions would enable stakeholders to act quickly to reduce their financial losses. This study developed an advanced bankruptcy prediction model using Support Vector Machines (SVM), Random Forest (RF), and Artificial Neural Network (ANN) algorithms based on datasets from the UCI machine learning repository. The core contribution of this research is the establishment of a hybrid model that effectively combines multiple machine learning (ML) algorithms with advanced data with the Synthetic minority oversampling technique Tomek (SMOTE Tomek) or SMOTE- Edited Nearest Neighbor (SMOTE-ENN) resampling data technique to improve bankruptcy prediction accuracy. Additionally, a wrapper-based feature selection (FS) utilizing Binary Particle Swarm Optimization (BPSO) was utilized to find an optimal feature subset and boost the model’s predictive performance. After selecting the best features, these were used to train the three ML algorithms, and hyper-parameter optimization was implemented to boost model performance. From the results measured by evaluation metrics, the proposed model ANN with the combination of parameter tuning, feature selection algorithm, SMOTE-ENN, and optimal hyper-parameters demonstrates superior performance compared to traditional methods, achieving an F1 Score of 98.5% and an accuracy of 98.6%. The results suggest that the predictive performance of bankruptcy models can be significantly enhanced by integrating multiple analytical methodologies.  This approach not only improves the accuracy but also the reliability of financial risk assessments, providing valuable insights for investors, financial analysts, and policymakers. The success of the model opens avenues for further research into hybrid predictive models in various sectors of finance, potentially transforming risk assessment methodologies.https://ijtech.eng.ui.ac.id/article/view/7227artificial neural networksbankruptcy predictionbinary particle swarmoptimization random forestsynthetic minority oversampling technique (smote)
spellingShingle Hung V. Pham
Tuan Chu
Tuan M. Le
Hieu M. Tran
Huong T.K. Tran
Khanh N. Yen
Son V. T. Dao
Comprehensive Evaluation of Bankruptcy Prediction in Taiwanese Firms Using Multiple Machine Learning Models
International Journal of Technology
artificial neural networks
bankruptcy prediction
binary particle swarm
optimization random forest
synthetic minority oversampling technique (smote)
title Comprehensive Evaluation of Bankruptcy Prediction in Taiwanese Firms Using Multiple Machine Learning Models
title_full Comprehensive Evaluation of Bankruptcy Prediction in Taiwanese Firms Using Multiple Machine Learning Models
title_fullStr Comprehensive Evaluation of Bankruptcy Prediction in Taiwanese Firms Using Multiple Machine Learning Models
title_full_unstemmed Comprehensive Evaluation of Bankruptcy Prediction in Taiwanese Firms Using Multiple Machine Learning Models
title_short Comprehensive Evaluation of Bankruptcy Prediction in Taiwanese Firms Using Multiple Machine Learning Models
title_sort comprehensive evaluation of bankruptcy prediction in taiwanese firms using multiple machine learning models
topic artificial neural networks
bankruptcy prediction
binary particle swarm
optimization random forest
synthetic minority oversampling technique (smote)
url https://ijtech.eng.ui.ac.id/article/view/7227
work_keys_str_mv AT hungvpham comprehensiveevaluationofbankruptcypredictionintaiwanesefirmsusingmultiplemachinelearningmodels
AT tuanchu comprehensiveevaluationofbankruptcypredictionintaiwanesefirmsusingmultiplemachinelearningmodels
AT tuanmle comprehensiveevaluationofbankruptcypredictionintaiwanesefirmsusingmultiplemachinelearningmodels
AT hieumtran comprehensiveevaluationofbankruptcypredictionintaiwanesefirmsusingmultiplemachinelearningmodels
AT huongtktran comprehensiveevaluationofbankruptcypredictionintaiwanesefirmsusingmultiplemachinelearningmodels
AT khanhnyen comprehensiveevaluationofbankruptcypredictionintaiwanesefirmsusingmultiplemachinelearningmodels
AT sonvtdao comprehensiveevaluationofbankruptcypredictionintaiwanesefirmsusingmultiplemachinelearningmodels