No Cover Image

Journal article 438 views

MODELING CREDIT APPROVAL DATA WITH NEURAL NETWORKS: AN EXPERIMENTAL INVESTIGATION AND OPTIMIZATION

Chi GUOTAI, Mohammad Abedin Orcid Logo, Fahmida E–MOULA

Journal of Business Economics and Management, Volume: 18, Issue: 2, Pages: 224 - 240

Swansea University Author: Mohammad Abedin Orcid Logo

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

Abstract

This study proposes an investigation and optimization of Multi-Layer Perceptron (MLP) based artificial neural networks (ANN) credit prediction model, combine with the effect of different ratios of training to testing instances over five real-world credit databases. As an outcome from the alteration...

Full description

Published in: Journal of Business Economics and Management
ISSN: 1611-1699 2029-4433
Published: Vilnius Gediminas Technical University
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa64252
first_indexed 2023-09-19T10:49:59Z
last_indexed 2024-11-25T14:13:43Z
id cronfa64252
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2023-09-20T10:34:57.3450303</datestamp><bib-version>v2</bib-version><id>64252</id><entry>2023-08-31</entry><title>MODELING CREDIT APPROVAL DATA WITH NEURAL NETWORKS: AN EXPERIMENTAL INVESTIGATION AND OPTIMIZATION</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>2023-08-31</date><deptcode>CBAE</deptcode><abstract>This study proposes an investigation and optimization of Multi-Layer Perceptron (MLP) based artificial neural networks (ANN) credit prediction model, combine with the effect of different ratios of training to testing instances over five real-world credit databases. As an outcome from the alteration procedure, three different types of hidden units [K = 9 (ANN&#x2013;1), K = 10 (ANN&#x2013;2), K = 23 (ANN&#x2013;3)] are chosen through the pilot experiments and execute, therefore, 45 (5&#xD7;3&#xD7;3) unique neural models. Experimental results indicate that &#x201C;the neural architecture with ten hidden units&#x201D; is proposed as an optimal approach to classifying the credit information. With these contributions, therefore, we complement previous evidence and modernize the methods of credit prediction modeling. This study, however, has realistic implications for bank managers and other stakeholders to delineate the risk profile of the credit customers.</abstract><type>Journal Article</type><journal>Journal of Business Economics and Management</journal><volume>18</volume><journalNumber>2</journalNumber><paginationStart>224</paginationStart><paginationEnd>240</paginationEnd><publisher>Vilnius Gediminas Technical University</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1611-1699</issnPrint><issnElectronic>2029-4433</issnElectronic><keywords>Credit prediction, neural networks, Multi-Layer Perceptron, hidden neurons, alteration experiments, investigation and optimization</keywords><publishedDay>0</publishedDay><publishedMonth>0</publishedMonth><publishedYear>0</publishedYear><publishedDate>0001-01-01</publishedDate><doi>10.3846/16111699.2017.1280844</doi><url>http://dx.doi.org/10.3846/16111699.2017.1280844</url><notes/><college>COLLEGE NANME</college><department>Management School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>CBAE</DepartmentCode><institution>Swansea University</institution><apcterm/><funders/><projectreference/><lastEdited>2023-09-20T10:34:57.3450303</lastEdited><Created>2023-08-31T17:53:40.2041675</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>Chi</firstname><surname>GUOTAI</surname><order>1</order></author><author><firstname>Mohammad</firstname><surname>Abedin</surname><orcid>0000-0002-4688-0619</orcid><order>2</order></author><author><firstname>Fahmida</firstname><surname>E&#x2013;MOULA</surname><order>3</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2023-09-20T10:34:57.3450303 v2 64252 2023-08-31 MODELING CREDIT APPROVAL DATA WITH NEURAL NETWORKS: AN EXPERIMENTAL INVESTIGATION AND OPTIMIZATION 4ed8c020eae0c9bec4f5d9495d86d415 0000-0002-4688-0619 Mohammad Abedin Mohammad Abedin true false 2023-08-31 CBAE This study proposes an investigation and optimization of Multi-Layer Perceptron (MLP) based artificial neural networks (ANN) credit prediction model, combine with the effect of different ratios of training to testing instances over five real-world credit databases. As an outcome from the alteration procedure, three different types of hidden units [K = 9 (ANN–1), K = 10 (ANN–2), K = 23 (ANN–3)] are chosen through the pilot experiments and execute, therefore, 45 (5×3×3) unique neural models. Experimental results indicate that “the neural architecture with ten hidden units” is proposed as an optimal approach to classifying the credit information. With these contributions, therefore, we complement previous evidence and modernize the methods of credit prediction modeling. This study, however, has realistic implications for bank managers and other stakeholders to delineate the risk profile of the credit customers. Journal Article Journal of Business Economics and Management 18 2 224 240 Vilnius Gediminas Technical University 1611-1699 2029-4433 Credit prediction, neural networks, Multi-Layer Perceptron, hidden neurons, alteration experiments, investigation and optimization 0 0 0 0001-01-01 10.3846/16111699.2017.1280844 http://dx.doi.org/10.3846/16111699.2017.1280844 COLLEGE NANME Management School COLLEGE CODE CBAE Swansea University 2023-09-20T10:34:57.3450303 2023-08-31T17:53:40.2041675 Faculty of Humanities and Social Sciences School of Management - Accounting and Finance Chi GUOTAI 1 Mohammad Abedin 0000-0002-4688-0619 2 Fahmida E–MOULA 3
title MODELING CREDIT APPROVAL DATA WITH NEURAL NETWORKS: AN EXPERIMENTAL INVESTIGATION AND OPTIMIZATION
spellingShingle MODELING CREDIT APPROVAL DATA WITH NEURAL NETWORKS: AN EXPERIMENTAL INVESTIGATION AND OPTIMIZATION
Mohammad Abedin
title_short MODELING CREDIT APPROVAL DATA WITH NEURAL NETWORKS: AN EXPERIMENTAL INVESTIGATION AND OPTIMIZATION
title_full MODELING CREDIT APPROVAL DATA WITH NEURAL NETWORKS: AN EXPERIMENTAL INVESTIGATION AND OPTIMIZATION
title_fullStr MODELING CREDIT APPROVAL DATA WITH NEURAL NETWORKS: AN EXPERIMENTAL INVESTIGATION AND OPTIMIZATION
title_full_unstemmed MODELING CREDIT APPROVAL DATA WITH NEURAL NETWORKS: AN EXPERIMENTAL INVESTIGATION AND OPTIMIZATION
title_sort MODELING CREDIT APPROVAL DATA WITH NEURAL NETWORKS: AN EXPERIMENTAL INVESTIGATION AND OPTIMIZATION
author_id_str_mv 4ed8c020eae0c9bec4f5d9495d86d415
author_id_fullname_str_mv 4ed8c020eae0c9bec4f5d9495d86d415_***_Mohammad Abedin
author Mohammad Abedin
author2 Chi GUOTAI
Mohammad Abedin
Fahmida E–MOULA
format Journal article
container_title Journal of Business Economics and Management
container_volume 18
container_issue 2
container_start_page 224
institution Swansea University
issn 1611-1699
2029-4433
doi_str_mv 10.3846/16111699.2017.1280844
publisher Vilnius Gediminas Technical University
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/10.3846/16111699.2017.1280844
document_store_str 0
active_str 0
description This study proposes an investigation and optimization of Multi-Layer Perceptron (MLP) based artificial neural networks (ANN) credit prediction model, combine with the effect of different ratios of training to testing instances over five real-world credit databases. As an outcome from the alteration procedure, three different types of hidden units [K = 9 (ANN–1), K = 10 (ANN–2), K = 23 (ANN–3)] are chosen through the pilot experiments and execute, therefore, 45 (5×3×3) unique neural models. Experimental results indicate that “the neural architecture with ten hidden units” is proposed as an optimal approach to classifying the credit information. With these contributions, therefore, we complement previous evidence and modernize the methods of credit prediction modeling. This study, however, has realistic implications for bank managers and other stakeholders to delineate the risk profile of the credit customers.
published_date 0001-01-01T17:57:12Z
_version_ 1831844061821009920
score 11.058631