No Cover Image

Journal article 12 views

Class imbalance Bayesian model averaging for consumer loan default prediction: The role of soft credit information

Futian Weng Orcid Logo, Miao Zhu, Mike Buckle, Petr Hajek Orcid Logo, Mohammad Abedin Orcid Logo

Research in International Business and Finance, Volume: 74, Start page: 102722

Swansea University Author: Mohammad Abedin Orcid Logo

Full text not available from this repository: check for access using links below.

Check full text

DOI (Published version): 10.1016/j.ribaf.2024.102722

Abstract

This study investigates the predictive value of soft information for consumer loan defaults. We propose a novel framework to address class imbalance by utilizing the concept of Bayesian model averaging. Specifically, we assign unequal weights to machine learning sub-models that incorporate different...

Full description

Published in: Research in International Business and Finance
ISSN: 0275-5319
Published: Elsevier BV 2025
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa68662
first_indexed 2025-01-09T20:34:06Z
last_indexed 2025-01-09T20:34:06Z
id cronfa68662
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-01-08T12:59:39.3957347</datestamp><bib-version>v2</bib-version><id>68662</id><entry>2025-01-08</entry><title>Class imbalance Bayesian model averaging for consumer loan default prediction: The role of soft credit information</title><swanseaauthors><author><sid>4ed8c020eae0c9bec4f5d9495d86d415</sid><ORCID>0000-0002-4688-0619</ORCID><firstname>Mohammad</firstname><surname>Abedin</surname><name>Mohammad Abedin</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-01-08</date><deptcode>CBAE</deptcode><abstract>This study investigates the predictive value of soft information for consumer loan defaults. We propose a novel framework to address class imbalance by utilizing the concept of Bayesian model averaging. Specifically, we assign unequal weights to machine learning sub-models that incorporate different combinations of variables, thereby creating an accurate and robust model for predicting consumer loan defaults. Additionally, this framework incorporates the Shapley additive explanations (SHAP) method to estimate individual contributions and employs the Bayesian information criterion to assess the variable contributions of the sub-models. We validate the effectiveness and robustness of our proposed method using authentic loan data and publicly available credit default records from a prominent consumer platform in China. Our empirical research suggests that the characteristics of user online behavior are significantly predictive of loan defaults, demonstrating asymmetry at different stages of default.</abstract><type>Journal Article</type><journal>Research in International Business and Finance</journal><volume>74</volume><journalNumber/><paginationStart>102722</paginationStart><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0275-5319</issnPrint><issnElectronic/><keywords>Consumer loan, Soft credit information, Class imbalance, Bayesian model averaging, Variable contribution</keywords><publishedDay>1</publishedDay><publishedMonth>2</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-02-01</publishedDate><doi>10.1016/j.ribaf.2024.102722</doi><url>https://doi.org/10.1016/j.ribaf.2024.102722</url><notes/><college>COLLEGE NANME</college><department>Management School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>CBAE</DepartmentCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders/><projectreference/><lastEdited>2025-01-08T12:59:39.3957347</lastEdited><Created>2025-01-08T12:55:02.8862269</Created><path><level id="1">Faculty of Humanities and Social Sciences</level><level id="2">School of Management - Business Management</level></path><authors><author><firstname>Futian</firstname><surname>Weng</surname><orcid>0000-0002-7982-8729</orcid><order>1</order></author><author><firstname>Miao</firstname><surname>Zhu</surname><order>2</order></author><author><firstname>Mike</firstname><surname>Buckle</surname><order>3</order></author><author><firstname>Petr</firstname><surname>Hajek</surname><orcid>0000-0001-5579-1215</orcid><order>4</order></author><author><firstname>Mohammad</firstname><surname>Abedin</surname><orcid>0000-0002-4688-0619</orcid><order>5</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2025-01-08T12:59:39.3957347 v2 68662 2025-01-08 Class imbalance Bayesian model averaging for consumer loan default prediction: The role of soft credit information 4ed8c020eae0c9bec4f5d9495d86d415 0000-0002-4688-0619 Mohammad Abedin Mohammad Abedin true false 2025-01-08 CBAE This study investigates the predictive value of soft information for consumer loan defaults. We propose a novel framework to address class imbalance by utilizing the concept of Bayesian model averaging. Specifically, we assign unequal weights to machine learning sub-models that incorporate different combinations of variables, thereby creating an accurate and robust model for predicting consumer loan defaults. Additionally, this framework incorporates the Shapley additive explanations (SHAP) method to estimate individual contributions and employs the Bayesian information criterion to assess the variable contributions of the sub-models. We validate the effectiveness and robustness of our proposed method using authentic loan data and publicly available credit default records from a prominent consumer platform in China. Our empirical research suggests that the characteristics of user online behavior are significantly predictive of loan defaults, demonstrating asymmetry at different stages of default. Journal Article Research in International Business and Finance 74 102722 Elsevier BV 0275-5319 Consumer loan, Soft credit information, Class imbalance, Bayesian model averaging, Variable contribution 1 2 2025 2025-02-01 10.1016/j.ribaf.2024.102722 https://doi.org/10.1016/j.ribaf.2024.102722 COLLEGE NANME Management School COLLEGE CODE CBAE Swansea University SU Library paid the OA fee (TA Institutional Deal) 2025-01-08T12:59:39.3957347 2025-01-08T12:55:02.8862269 Faculty of Humanities and Social Sciences School of Management - Business Management Futian Weng 0000-0002-7982-8729 1 Miao Zhu 2 Mike Buckle 3 Petr Hajek 0000-0001-5579-1215 4 Mohammad Abedin 0000-0002-4688-0619 5
title Class imbalance Bayesian model averaging for consumer loan default prediction: The role of soft credit information
spellingShingle Class imbalance Bayesian model averaging for consumer loan default prediction: The role of soft credit information
Mohammad Abedin
title_short Class imbalance Bayesian model averaging for consumer loan default prediction: The role of soft credit information
title_full Class imbalance Bayesian model averaging for consumer loan default prediction: The role of soft credit information
title_fullStr Class imbalance Bayesian model averaging for consumer loan default prediction: The role of soft credit information
title_full_unstemmed Class imbalance Bayesian model averaging for consumer loan default prediction: The role of soft credit information
title_sort Class imbalance Bayesian model averaging for consumer loan default prediction: The role of soft credit information
author_id_str_mv 4ed8c020eae0c9bec4f5d9495d86d415
author_id_fullname_str_mv 4ed8c020eae0c9bec4f5d9495d86d415_***_Mohammad Abedin
author Mohammad Abedin
author2 Futian Weng
Miao Zhu
Mike Buckle
Petr Hajek
Mohammad Abedin
format Journal article
container_title Research in International Business and Finance
container_volume 74
container_start_page 102722
publishDate 2025
institution Swansea University
issn 0275-5319
doi_str_mv 10.1016/j.ribaf.2024.102722
publisher Elsevier BV
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 - Business Management{{{_:::_}}}Faculty of Humanities and Social Sciences{{{_:::_}}}School of Management - Business Management
url https://doi.org/10.1016/j.ribaf.2024.102722
document_store_str 0
active_str 0
description This study investigates the predictive value of soft information for consumer loan defaults. We propose a novel framework to address class imbalance by utilizing the concept of Bayesian model averaging. Specifically, we assign unequal weights to machine learning sub-models that incorporate different combinations of variables, thereby creating an accurate and robust model for predicting consumer loan defaults. Additionally, this framework incorporates the Shapley additive explanations (SHAP) method to estimate individual contributions and employs the Bayesian information criterion to assess the variable contributions of the sub-models. We validate the effectiveness and robustness of our proposed method using authentic loan data and publicly available credit default records from a prominent consumer platform in China. Our empirical research suggests that the characteristics of user online behavior are significantly predictive of loan defaults, demonstrating asymmetry at different stages of default.
published_date 2025-02-01T20:37:09Z
_version_ 1821348650925686784
score 11.04748

Similar Items