Journal article 117 views 38 downloads
Combining weighted SMOTE with ensemble learning for the class-imbalanced prediction of small business credit risk
Complex and Intelligent Systems, Volume: 9, Issue: 4, Pages: 3559 - 3579
Swansea University Author: Abedin Abedin
-
PDF | Version of Record
© The Author(s) 2021. Distributed under the terms of a Creative Commons Attribution 4.0 License (CC BY 4.0).
Download (1.23MB)
DOI (Published version): 10.1007/s40747-021-00614-4
Abstract
In small business credit risk assessment, the default and nondefault classes are highly imbalanced. To overcome this problem, this study proposes an extended ensemble approach rooted in the weighted synthetic minority oversampling technique (WSMOTE), which is called WSMOTE-ensemble. The proposed ens...
Published in: | Complex and Intelligent Systems |
---|---|
ISSN: | 2199-4536 2198-6053 |
Published: |
Springer Science and Business Media LLC
2023
|
Online Access: |
Check full text
|
URI: | https://cronfa.swan.ac.uk/Record/cronfa64260 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
first_indexed |
2023-09-18T16:27:22Z |
---|---|
last_indexed |
2023-09-18T16:27:22Z |
id |
cronfa64260 |
recordtype |
SURis |
fullrecord |
<?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>64260</id><entry>2023-08-31</entry><title>Combining weighted SMOTE with ensemble learning for the class-imbalanced prediction of small business credit risk</title><swanseaauthors><author><sid>4ed8c020eae0c9bec4f5d9495d86d415</sid><firstname>Abedin</firstname><surname>Abedin</surname><name>Abedin Abedin</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-08-31</date><deptcode>BAF</deptcode><abstract>In small business credit risk assessment, the default and nondefault classes are highly imbalanced. To overcome this problem, this study proposes an extended ensemble approach rooted in the weighted synthetic minority oversampling technique (WSMOTE), which is called WSMOTE-ensemble. The proposed ensemble classifier hybridizes WSMOTE and Bagging with sampling composite mixtures to guarantee the robustness and variability of the generated synthetic instances and, thus, minimize the small business class-skewed constraints linked to default and nondefault instances. The original small business dataset used in this study was taken from 3111 records from a Chinese commercial bank. By implementing a thorough experimental study of extensively skewed data-modeling scenarios, a multilevel experimental setting was established for a rare event domain. Based on the proper evaluation measures, this study proposes that the random forest classifier used in the WSMOTE-ensemble model provides a good trade-off between the performance on default class and that of nondefault class. The ensemble solution improved the accuracy of the minority class by 15.16% in comparison with its competitors. This study also shows that sampling methods outperform nonsampling algorithms. With these contributions, this study fills a noteworthy knowledge gap and adds several unique insights regarding the prediction of small business credit risk.</abstract><type>Journal Article</type><journal>Complex and Intelligent Systems</journal><volume>9</volume><journalNumber>4</journalNumber><paginationStart>3559</paginationStart><paginationEnd>3579</paginationEnd><publisher>Springer Science and Business Media LLC</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>2199-4536</issnPrint><issnElectronic>2198-6053</issnElectronic><keywords>Small business, Credit risk, Imbalanced data, Oversampling, Weighted SMOTE, Ensemble learning</keywords><publishedDay>31</publishedDay><publishedMonth>8</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-08-31</publishedDate><doi>10.1007/s40747-021-00614-4</doi><url>http://dx.doi.org/10.1007/s40747-021-00614-4</url><notes/><college>COLLEGE NANME</college><department>Accounting and Finance</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>BAF</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>This work has been supported by the Key Projects of National Natural Science Foundation of China (71731003 and 71431002), the General Projects of National Natural Science Foundation of China (71471027 and 71873103), the National Social Science Foundation of China (16BTJ017), the Youth Project of National Natural Science Foundation of China (71601041), the scientific research project of the Czech Sciences Foundation Grant (19-15498S), the Aderi Intelligent Technology (Xiamen) Co and Bank of Dalian as well as Postal Savings Bank of China.</funders><projectreference/><lastEdited>2023-09-20T10:27:13.2855708</lastEdited><Created>2023-08-31T17:58:52.9308496</Created><path><level id="1">Faculty of Humanities and Social Sciences</level><level id="2">School of Management - Accounting and Finance</level></path><authors><author><firstname>Abedin</firstname><surname>Abedin</surname><order>1</order></author><author><firstname>Chi</firstname><surname>Guotai</surname><order>2</order></author><author><firstname>Petr</firstname><surname>Hajek</surname><order>3</order></author><author><firstname>Tong</firstname><surname>Zhang</surname><order>4</order></author></authors><documents><document><filename>64260__28567__561dc4f2b9e64680b0ef89b878321b14.pdf</filename><originalFilename>64260.VOR.pdf</originalFilename><uploaded>2023-09-18T17:26:49.7376340</uploaded><type>Output</type><contentLength>1291323</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© The Author(s) 2021. Distributed under the terms of a Creative Commons Attribution 4.0 License (CC BY 4.0).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807> |
spelling |
v2 64260 2023-08-31 Combining weighted SMOTE with ensemble learning for the class-imbalanced prediction of small business credit risk 4ed8c020eae0c9bec4f5d9495d86d415 Abedin Abedin Abedin Abedin true false 2023-08-31 BAF In small business credit risk assessment, the default and nondefault classes are highly imbalanced. To overcome this problem, this study proposes an extended ensemble approach rooted in the weighted synthetic minority oversampling technique (WSMOTE), which is called WSMOTE-ensemble. The proposed ensemble classifier hybridizes WSMOTE and Bagging with sampling composite mixtures to guarantee the robustness and variability of the generated synthetic instances and, thus, minimize the small business class-skewed constraints linked to default and nondefault instances. The original small business dataset used in this study was taken from 3111 records from a Chinese commercial bank. By implementing a thorough experimental study of extensively skewed data-modeling scenarios, a multilevel experimental setting was established for a rare event domain. Based on the proper evaluation measures, this study proposes that the random forest classifier used in the WSMOTE-ensemble model provides a good trade-off between the performance on default class and that of nondefault class. The ensemble solution improved the accuracy of the minority class by 15.16% in comparison with its competitors. This study also shows that sampling methods outperform nonsampling algorithms. With these contributions, this study fills a noteworthy knowledge gap and adds several unique insights regarding the prediction of small business credit risk. Journal Article Complex and Intelligent Systems 9 4 3559 3579 Springer Science and Business Media LLC 2199-4536 2198-6053 Small business, Credit risk, Imbalanced data, Oversampling, Weighted SMOTE, Ensemble learning 31 8 2023 2023-08-31 10.1007/s40747-021-00614-4 http://dx.doi.org/10.1007/s40747-021-00614-4 COLLEGE NANME Accounting and Finance COLLEGE CODE BAF Swansea University This work has been supported by the Key Projects of National Natural Science Foundation of China (71731003 and 71431002), the General Projects of National Natural Science Foundation of China (71471027 and 71873103), the National Social Science Foundation of China (16BTJ017), the Youth Project of National Natural Science Foundation of China (71601041), the scientific research project of the Czech Sciences Foundation Grant (19-15498S), the Aderi Intelligent Technology (Xiamen) Co and Bank of Dalian as well as Postal Savings Bank of China. 2023-09-20T10:27:13.2855708 2023-08-31T17:58:52.9308496 Faculty of Humanities and Social Sciences School of Management - Accounting and Finance Abedin Abedin 1 Chi Guotai 2 Petr Hajek 3 Tong Zhang 4 64260__28567__561dc4f2b9e64680b0ef89b878321b14.pdf 64260.VOR.pdf 2023-09-18T17:26:49.7376340 Output 1291323 application/pdf Version of Record true © The Author(s) 2021. Distributed under the terms of a Creative Commons Attribution 4.0 License (CC BY 4.0). true eng https://creativecommons.org/licenses/by/4.0/ |
title |
Combining weighted SMOTE with ensemble learning for the class-imbalanced prediction of small business credit risk |
spellingShingle |
Combining weighted SMOTE with ensemble learning for the class-imbalanced prediction of small business credit risk Abedin Abedin |
title_short |
Combining weighted SMOTE with ensemble learning for the class-imbalanced prediction of small business credit risk |
title_full |
Combining weighted SMOTE with ensemble learning for the class-imbalanced prediction of small business credit risk |
title_fullStr |
Combining weighted SMOTE with ensemble learning for the class-imbalanced prediction of small business credit risk |
title_full_unstemmed |
Combining weighted SMOTE with ensemble learning for the class-imbalanced prediction of small business credit risk |
title_sort |
Combining weighted SMOTE with ensemble learning for the class-imbalanced prediction of small business credit risk |
author_id_str_mv |
4ed8c020eae0c9bec4f5d9495d86d415 |
author_id_fullname_str_mv |
4ed8c020eae0c9bec4f5d9495d86d415_***_Abedin Abedin |
author |
Abedin Abedin |
author2 |
Abedin Abedin Chi Guotai Petr Hajek Tong Zhang |
format |
Journal article |
container_title |
Complex and Intelligent Systems |
container_volume |
9 |
container_issue |
4 |
container_start_page |
3559 |
publishDate |
2023 |
institution |
Swansea University |
issn |
2199-4536 2198-6053 |
doi_str_mv |
10.1007/s40747-021-00614-4 |
publisher |
Springer Science and Business Media LLC |
college_str |
Faculty of Humanities and Social Sciences |
hierarchytype |
|
hierarchy_top_id |
facultyofhumanitiesandsocialsciences |
hierarchy_top_title |
Faculty of Humanities and Social Sciences |
hierarchy_parent_id |
facultyofhumanitiesandsocialsciences |
hierarchy_parent_title |
Faculty of Humanities and Social Sciences |
department_str |
School of Management - Accounting and Finance{{{_:::_}}}Faculty of Humanities and Social Sciences{{{_:::_}}}School of Management - Accounting and Finance |
url |
http://dx.doi.org/10.1007/s40747-021-00614-4 |
document_store_str |
1 |
active_str |
0 |
description |
In small business credit risk assessment, the default and nondefault classes are highly imbalanced. To overcome this problem, this study proposes an extended ensemble approach rooted in the weighted synthetic minority oversampling technique (WSMOTE), which is called WSMOTE-ensemble. The proposed ensemble classifier hybridizes WSMOTE and Bagging with sampling composite mixtures to guarantee the robustness and variability of the generated synthetic instances and, thus, minimize the small business class-skewed constraints linked to default and nondefault instances. The original small business dataset used in this study was taken from 3111 records from a Chinese commercial bank. By implementing a thorough experimental study of extensively skewed data-modeling scenarios, a multilevel experimental setting was established for a rare event domain. Based on the proper evaluation measures, this study proposes that the random forest classifier used in the WSMOTE-ensemble model provides a good trade-off between the performance on default class and that of nondefault class. The ensemble solution improved the accuracy of the minority class by 15.16% in comparison with its competitors. This study also shows that sampling methods outperform nonsampling algorithms. With these contributions, this study fills a noteworthy knowledge gap and adds several unique insights regarding the prediction of small business credit risk. |
published_date |
2023-08-31T10:27:10Z |
_version_ |
1777548164806475776 |
score |
11.012678 |