A Cluster-Based Boosting Algorithm for Bankruptcy Prediction in a Highly Imbalanced Dataset
Bankruptcy prediction has been a popular and challenging research topic in both computer science and economics due to its importance to financial institutions, fund managers, lenders, governments, as well as economic stakeholders in recent years. In a bankruptcy dataset, the problem of class imbalan...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-07-01
|
Series: | Symmetry |
Subjects: | |
Online Access: | http://www.mdpi.com/2073-8994/10/7/250 |
id |
doaj-164ae8b892be4c1bb2f86d7314e1a3b5 |
---|---|
record_format |
Article |
spelling |
doaj-164ae8b892be4c1bb2f86d7314e1a3b52020-11-25T00:55:58ZengMDPI AGSymmetry2073-89942018-07-0110725010.3390/sym10070250sym10070250A Cluster-Based Boosting Algorithm for Bankruptcy Prediction in a Highly Imbalanced DatasetTuong Le0Le Hoang Son1Minh Thanh Vo2Mi Young Lee3Sung Wook Baik4Digital Contents Research Institute, Sejong University, Seoul 143-747, KoreaVNU University of Science, Vietnam National University, Hanoi, VietnamDigital Contents Research Institute, Sejong University, Seoul 143-747, KoreaDigital Contents Research Institute, Sejong University, Seoul 143-747, KoreaDigital Contents Research Institute, Sejong University, Seoul 143-747, KoreaBankruptcy prediction has been a popular and challenging research topic in both computer science and economics due to its importance to financial institutions, fund managers, lenders, governments, as well as economic stakeholders in recent years. In a bankruptcy dataset, the problem of class imbalance, in which the number of bankruptcy companies is smaller than the number of normal companies, leads to a standard classification algorithm that does not work well. Therefore, this study proposes a cluster-based boosting algorithm as well as a robust framework using the CBoost algorithm and Instance Hardness Threshold (RFCI) for effective bankruptcy prediction of a financial dataset. This framework first resamples the imbalance dataset by the undersampling method using Instance Hardness Threshold (IHT), which is used to remove the noise instances having large IHT value in the majority class. Then, this study proposes a Cluster-based Boosting algorithm, namely CBoost, for dealing with the class imbalance. In this algorithm, the majority class will be clustered into a number of clusters. The distance from each sample to its closest centroid will be used to initialize its weight. This algorithm will perform several iterations for finding weak classifiers and combining them to create a strong classifier. The resample set resulting from the previous module, will be used to train CBoost, which will be used to predict bankruptcy for the validation set. The proposed framework is verified by the Korean bankruptcy dataset (KBD), which has a very small balancing ratio in both the training and the testing phases. The experimental results of this research show that the proposed framework achieves 86.8% in AUC (area under the ROC curve) and outperforms several methods for dealing with the imbalanced data problem for bankruptcy prediction such as GMBoost algorithm, the oversampling-based method using SMOTEENN, and the clustering-based undersampling method for bankruptcy prediction in the experimental dataset.http://www.mdpi.com/2073-8994/10/7/250bankruptcy predictionundersampling techniquecluster-based boostingmachine learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Tuong Le Le Hoang Son Minh Thanh Vo Mi Young Lee Sung Wook Baik |
spellingShingle |
Tuong Le Le Hoang Son Minh Thanh Vo Mi Young Lee Sung Wook Baik A Cluster-Based Boosting Algorithm for Bankruptcy Prediction in a Highly Imbalanced Dataset Symmetry bankruptcy prediction undersampling technique cluster-based boosting machine learning |
author_facet |
Tuong Le Le Hoang Son Minh Thanh Vo Mi Young Lee Sung Wook Baik |
author_sort |
Tuong Le |
title |
A Cluster-Based Boosting Algorithm for Bankruptcy Prediction in a Highly Imbalanced Dataset |
title_short |
A Cluster-Based Boosting Algorithm for Bankruptcy Prediction in a Highly Imbalanced Dataset |
title_full |
A Cluster-Based Boosting Algorithm for Bankruptcy Prediction in a Highly Imbalanced Dataset |
title_fullStr |
A Cluster-Based Boosting Algorithm for Bankruptcy Prediction in a Highly Imbalanced Dataset |
title_full_unstemmed |
A Cluster-Based Boosting Algorithm for Bankruptcy Prediction in a Highly Imbalanced Dataset |
title_sort |
cluster-based boosting algorithm for bankruptcy prediction in a highly imbalanced dataset |
publisher |
MDPI AG |
series |
Symmetry |
issn |
2073-8994 |
publishDate |
2018-07-01 |
description |
Bankruptcy prediction has been a popular and challenging research topic in both computer science and economics due to its importance to financial institutions, fund managers, lenders, governments, as well as economic stakeholders in recent years. In a bankruptcy dataset, the problem of class imbalance, in which the number of bankruptcy companies is smaller than the number of normal companies, leads to a standard classification algorithm that does not work well. Therefore, this study proposes a cluster-based boosting algorithm as well as a robust framework using the CBoost algorithm and Instance Hardness Threshold (RFCI) for effective bankruptcy prediction of a financial dataset. This framework first resamples the imbalance dataset by the undersampling method using Instance Hardness Threshold (IHT), which is used to remove the noise instances having large IHT value in the majority class. Then, this study proposes a Cluster-based Boosting algorithm, namely CBoost, for dealing with the class imbalance. In this algorithm, the majority class will be clustered into a number of clusters. The distance from each sample to its closest centroid will be used to initialize its weight. This algorithm will perform several iterations for finding weak classifiers and combining them to create a strong classifier. The resample set resulting from the previous module, will be used to train CBoost, which will be used to predict bankruptcy for the validation set. The proposed framework is verified by the Korean bankruptcy dataset (KBD), which has a very small balancing ratio in both the training and the testing phases. The experimental results of this research show that the proposed framework achieves 86.8% in AUC (area under the ROC curve) and outperforms several methods for dealing with the imbalanced data problem for bankruptcy prediction such as GMBoost algorithm, the oversampling-based method using SMOTEENN, and the clustering-based undersampling method for bankruptcy prediction in the experimental dataset. |
topic |
bankruptcy prediction undersampling technique cluster-based boosting machine learning |
url |
http://www.mdpi.com/2073-8994/10/7/250 |
work_keys_str_mv |
AT tuongle aclusterbasedboostingalgorithmforbankruptcypredictioninahighlyimbalanceddataset AT lehoangson aclusterbasedboostingalgorithmforbankruptcypredictioninahighlyimbalanceddataset AT minhthanhvo aclusterbasedboostingalgorithmforbankruptcypredictioninahighlyimbalanceddataset AT miyounglee aclusterbasedboostingalgorithmforbankruptcypredictioninahighlyimbalanceddataset AT sungwookbaik aclusterbasedboostingalgorithmforbankruptcypredictioninahighlyimbalanceddataset AT tuongle clusterbasedboostingalgorithmforbankruptcypredictioninahighlyimbalanceddataset AT lehoangson clusterbasedboostingalgorithmforbankruptcypredictioninahighlyimbalanceddataset AT minhthanhvo clusterbasedboostingalgorithmforbankruptcypredictioninahighlyimbalanceddataset AT miyounglee clusterbasedboostingalgorithmforbankruptcypredictioninahighlyimbalanceddataset AT sungwookbaik clusterbasedboostingalgorithmforbankruptcypredictioninahighlyimbalanceddataset |
_version_ |
1725228671037341696 |