No Cover Image

Journal article 301 views 664 downloads

An explainable federated learning and blockchain-based secure credit modeling method

Fan Yang Orcid Logo, Mohammad Abedin Orcid Logo, Petr Hajek Orcid Logo

European Journal of Operational Research, Volume: 317, Issue: 2

Swansea University Author: Mohammad Abedin Orcid Logo

  • 64204.AAM.pdf

    PDF | Accepted Manuscript

    Author accepted manuscript document released under the terms of a Creative Commons CC BY-NC-ND licence.

    Download (1.22MB)

Check full text

DOI (Published version): 10.1016/j.ejor.2023.08.040

Abstract

Federated learning has drawn a lot of interest as a powerful technological solution to the “credit data silo” problem. The interpretability of federated learning is a crucial issue due to the lack of user interaction and the complexity of credit data monitoring. We advocate the importance of a credi...

Full description

Published in: European Journal of Operational Research
ISSN: 0377-2217
Published: Elsevier BV 2024
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa64204
first_indexed 2023-09-25T13:31:51Z
last_indexed 2024-11-25T14:13:38Z
id cronfa64204
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2024-09-19T09:45:27.3877721</datestamp><bib-version>v2</bib-version><id>64204</id><entry>2023-08-31</entry><title>An explainable federated learning and blockchain-based secure credit modeling method</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>Federated learning has drawn a lot of interest as a powerful technological solution to the &#x201C;credit data silo&#x201D; problem. The interpretability of federated learning is a crucial issue due to the lack of user interaction and the complexity of credit data monitoring. We advocate the importance of a credit data processing-as-a-service model, which completes conventional credit models in local environments, in order to overcome these restrictions. In particular, we describe an explainable federated learning and blockchain-based credit scoring system (EFCS) in this work. First, we propose an explainable federated learning method with controllable machine learning efficiency and controllable credit model decision making, thus having controllable credit model complexity and transparent and traceable credit decision-making mechanism. Then, we suggest an explainable federated learning training mechanism for credit data that prevents leakage of the model gradients trained by individual nodes during the training of the overall model. Neither the credit data provider nor the data user has access to the raw data in the credit model training ecosystem. Therefore, privacy protection, model performance, and algorithm efficiency, the core triangular cornerstones of federated learning, when added with model interpretability, together constitute a more secure and trustworthy federated learning-based methodology, thus providing a more reliable service for credit model training and construction. The EFCS scheme is presented via simulations of different types of federated learning and their resistance to system attack, applying the proposed model to six different credit scoring datasets. Extensive experimental analyses support the efficiency, security, and explainability of the EFCS.</abstract><type>Journal Article</type><journal>European Journal of Operational Research</journal><volume>317</volume><journalNumber>2</journalNumber><paginationStart/><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0377-2217</issnPrint><issnElectronic/><keywords>Analytics, Explainable federated learning, Privacy-preserving, Information leakage, Byzantine fault-tolerant</keywords><publishedDay>1</publishedDay><publishedMonth>9</publishedMonth><publishedYear>2024</publishedYear><publishedDate>2024-09-01</publishedDate><doi>10.1016/j.ejor.2023.08.040</doi><url>http://dx.doi.org/10.1016/j.ejor.2023.08.040</url><notes/><college>COLLEGE NANME</college><department>Management School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>CBAE</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>This research is supported by the Natural Science Basic Research Program of Shaanxi [Program No.2023-JC-YB-490]. This research is also supported by the Czech Sciences Foundation [grant number 22-22586S]; and the COST Action CA19130.</funders><projectreference/><lastEdited>2024-09-19T09:45:27.3877721</lastEdited><Created>2023-08-31T13:20:43.3018381</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>Fan</firstname><surname>Yang</surname><orcid>0000-0003-1842-1084</orcid><order>1</order></author><author><firstname>Mohammad</firstname><surname>Abedin</surname><orcid>0000-0002-4688-0619</orcid><order>2</order></author><author><firstname>Petr</firstname><surname>Hajek</surname><orcid>0000-0001-5579-1215</orcid><order>3</order></author></authors><documents><document><filename>64204__28723__f796b00bbc8b4e3cacd68ee5178bf3a7.pdf</filename><originalFilename>64204.AAM.pdf</originalFilename><uploaded>2023-10-06T14:33:30.0659862</uploaded><type>Output</type><contentLength>1283891</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2023-08-26T00:00:00.0000000</embargoDate><documentNotes>Author accepted manuscript document released under the terms of a Creative Commons CC BY-NC-ND licence.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by-nc-nd/4.0/deed.en</licence></document></documents><OutputDurs/></rfc1807>
spelling 2024-09-19T09:45:27.3877721 v2 64204 2023-08-31 An explainable federated learning and blockchain-based secure credit modeling method 4ed8c020eae0c9bec4f5d9495d86d415 0000-0002-4688-0619 Mohammad Abedin Mohammad Abedin true false 2023-08-31 CBAE Federated learning has drawn a lot of interest as a powerful technological solution to the “credit data silo” problem. The interpretability of federated learning is a crucial issue due to the lack of user interaction and the complexity of credit data monitoring. We advocate the importance of a credit data processing-as-a-service model, which completes conventional credit models in local environments, in order to overcome these restrictions. In particular, we describe an explainable federated learning and blockchain-based credit scoring system (EFCS) in this work. First, we propose an explainable federated learning method with controllable machine learning efficiency and controllable credit model decision making, thus having controllable credit model complexity and transparent and traceable credit decision-making mechanism. Then, we suggest an explainable federated learning training mechanism for credit data that prevents leakage of the model gradients trained by individual nodes during the training of the overall model. Neither the credit data provider nor the data user has access to the raw data in the credit model training ecosystem. Therefore, privacy protection, model performance, and algorithm efficiency, the core triangular cornerstones of federated learning, when added with model interpretability, together constitute a more secure and trustworthy federated learning-based methodology, thus providing a more reliable service for credit model training and construction. The EFCS scheme is presented via simulations of different types of federated learning and their resistance to system attack, applying the proposed model to six different credit scoring datasets. Extensive experimental analyses support the efficiency, security, and explainability of the EFCS. Journal Article European Journal of Operational Research 317 2 Elsevier BV 0377-2217 Analytics, Explainable federated learning, Privacy-preserving, Information leakage, Byzantine fault-tolerant 1 9 2024 2024-09-01 10.1016/j.ejor.2023.08.040 http://dx.doi.org/10.1016/j.ejor.2023.08.040 COLLEGE NANME Management School COLLEGE CODE CBAE Swansea University This research is supported by the Natural Science Basic Research Program of Shaanxi [Program No.2023-JC-YB-490]. This research is also supported by the Czech Sciences Foundation [grant number 22-22586S]; and the COST Action CA19130. 2024-09-19T09:45:27.3877721 2023-08-31T13:20:43.3018381 Faculty of Humanities and Social Sciences School of Management - Accounting and Finance Fan Yang 0000-0003-1842-1084 1 Mohammad Abedin 0000-0002-4688-0619 2 Petr Hajek 0000-0001-5579-1215 3 64204__28723__f796b00bbc8b4e3cacd68ee5178bf3a7.pdf 64204.AAM.pdf 2023-10-06T14:33:30.0659862 Output 1283891 application/pdf Accepted Manuscript true 2023-08-26T00:00:00.0000000 Author accepted manuscript document released under the terms of a Creative Commons CC BY-NC-ND licence. true eng https://creativecommons.org/licenses/by-nc-nd/4.0/deed.en
title An explainable federated learning and blockchain-based secure credit modeling method
spellingShingle An explainable federated learning and blockchain-based secure credit modeling method
Mohammad Abedin
title_short An explainable federated learning and blockchain-based secure credit modeling method
title_full An explainable federated learning and blockchain-based secure credit modeling method
title_fullStr An explainable federated learning and blockchain-based secure credit modeling method
title_full_unstemmed An explainable federated learning and blockchain-based secure credit modeling method
title_sort An explainable federated learning and blockchain-based secure credit modeling method
author_id_str_mv 4ed8c020eae0c9bec4f5d9495d86d415
author_id_fullname_str_mv 4ed8c020eae0c9bec4f5d9495d86d415_***_Mohammad Abedin
author Mohammad Abedin
author2 Fan Yang
Mohammad Abedin
Petr Hajek
format Journal article
container_title European Journal of Operational Research
container_volume 317
container_issue 2
publishDate 2024
institution Swansea University
issn 0377-2217
doi_str_mv 10.1016/j.ejor.2023.08.040
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 - Accounting and Finance{{{_:::_}}}Faculty of Humanities and Social Sciences{{{_:::_}}}School of Management - Accounting and Finance
url http://dx.doi.org/10.1016/j.ejor.2023.08.040
document_store_str 1
active_str 0
description Federated learning has drawn a lot of interest as a powerful technological solution to the “credit data silo” problem. The interpretability of federated learning is a crucial issue due to the lack of user interaction and the complexity of credit data monitoring. We advocate the importance of a credit data processing-as-a-service model, which completes conventional credit models in local environments, in order to overcome these restrictions. In particular, we describe an explainable federated learning and blockchain-based credit scoring system (EFCS) in this work. First, we propose an explainable federated learning method with controllable machine learning efficiency and controllable credit model decision making, thus having controllable credit model complexity and transparent and traceable credit decision-making mechanism. Then, we suggest an explainable federated learning training mechanism for credit data that prevents leakage of the model gradients trained by individual nodes during the training of the overall model. Neither the credit data provider nor the data user has access to the raw data in the credit model training ecosystem. Therefore, privacy protection, model performance, and algorithm efficiency, the core triangular cornerstones of federated learning, when added with model interpretability, together constitute a more secure and trustworthy federated learning-based methodology, thus providing a more reliable service for credit model training and construction. The EFCS scheme is presented via simulations of different types of federated learning and their resistance to system attack, applying the proposed model to six different credit scoring datasets. Extensive experimental analyses support the efficiency, security, and explainability of the EFCS.
published_date 2024-09-01T08:27:50Z
_version_ 1821936944756555776
score 11.048064

Similar Items