No Cover Image

Journal article 197 views

Fraud detection in capital markets: A novel machine learning approach

Ziwei Yi, Xinwei Cao, Xujin Pu, Yiding Wu, Zuyan Chen, Ameer Tamoor Khan, Adam Francis, Shuai Li

Expert Systems with Applications, Volume: 231, Start page: 120760

Swansea University Author: Adam Francis

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

Check full text

DOI (Published version): 10.1016/j.eswa.2023.120760

Abstract

Traditional auditing methods require collating massive amounts of financial indicators and related transaction data, which can be labor-intensive. Typical machine learning models are relatively weak for imbalanced data, and this work aims to focus on a novel approach to fraud detection. This paper p...

Full description

Published in: Expert Systems with Applications
ISSN: 0957-4174
Published: Elsevier BV 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa63635
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2023-06-21T13:17:44Z
last_indexed 2023-06-21T13:17:44Z
id cronfa63635
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>63635</id><entry>2023-06-13</entry><title>Fraud detection in capital markets: A novel machine learning approach</title><swanseaauthors><author><sid>8449248c17fec32f131097c0d1a768cc</sid><firstname>Adam</firstname><surname>Francis</surname><name>Adam Francis</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-06-13</date><deptcode>FGSEN</deptcode><abstract>Traditional auditing methods require collating massive amounts of financial indicators and related transaction data, which can be labor-intensive. Typical machine learning models are relatively weak for imbalanced data, and this work aims to focus on a novel approach to fraud detection. This paper presents a fraud detection framework via adopting a machine learning method integrated with a recently proposed meta-heuristics algorithm Egret Swarm Optimization Algorithm (ESOA). A cost-sensitive objective function and loss function were then constructed, and a non-linear model was used to map the predicted values into the labels of 0 (non-fraud) and 1 (fraud). In the experiment section, an AAER benchmark dataset collected by the UCB’s Center for Financial Reporting and Management is utilized to verify the performance of the proposed approach. A detailed comparison with recently proposed state-of-the-art algorithms such as Logit (67.20%), SVM-FK (62.60%), RUSBoost (72.60%), as well as BAS (84.90%) indicates that ESOA (96.27%) outperforms the other algorithms in terms of Accuracy (ACC), Sensitivity (SEN), Precision (PREC), and Area Under the Curve (AUC) metrics. To our knowledge, this is the highest fraud detection accuracy reported in the existing literature.</abstract><type>Journal Article</type><journal>Expert Systems with Applications</journal><volume>231</volume><journalNumber/><paginationStart>120760</paginationStart><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0957-4174</issnPrint><issnElectronic/><keywords/><publishedDay>30</publishedDay><publishedMonth>11</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-11-30</publishedDate><doi>10.1016/j.eswa.2023.120760</doi><url>http://dx.doi.org/10.1016/j.eswa.2023.120760</url><notes/><college>COLLEGE NANME</college><department>Science and Engineering - Faculty</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>FGSEN</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>This paper is partially supported by National Natural Science Foundation of China with grant number 72271109</funders><projectreference/><lastEdited>2023-09-04T12:42:10.0308232</lastEdited><Created>2023-06-13T14:20:10.8761894</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Electronic and Electrical Engineering</level></path><authors><author><firstname>Ziwei</firstname><surname>Yi</surname><order>1</order></author><author><firstname>Xinwei</firstname><surname>Cao</surname><order>2</order></author><author><firstname>Xujin</firstname><surname>Pu</surname><order>3</order></author><author><firstname>Yiding</firstname><surname>Wu</surname><order>4</order></author><author><firstname>Zuyan</firstname><surname>Chen</surname><order>5</order></author><author><firstname>Ameer Tamoor</firstname><surname>Khan</surname><order>6</order></author><author><firstname>Adam</firstname><surname>Francis</surname><order>7</order></author><author><firstname>Shuai</firstname><surname>Li</surname><order>8</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling v2 63635 2023-06-13 Fraud detection in capital markets: A novel machine learning approach 8449248c17fec32f131097c0d1a768cc Adam Francis Adam Francis true false 2023-06-13 FGSEN Traditional auditing methods require collating massive amounts of financial indicators and related transaction data, which can be labor-intensive. Typical machine learning models are relatively weak for imbalanced data, and this work aims to focus on a novel approach to fraud detection. This paper presents a fraud detection framework via adopting a machine learning method integrated with a recently proposed meta-heuristics algorithm Egret Swarm Optimization Algorithm (ESOA). A cost-sensitive objective function and loss function were then constructed, and a non-linear model was used to map the predicted values into the labels of 0 (non-fraud) and 1 (fraud). In the experiment section, an AAER benchmark dataset collected by the UCB’s Center for Financial Reporting and Management is utilized to verify the performance of the proposed approach. A detailed comparison with recently proposed state-of-the-art algorithms such as Logit (67.20%), SVM-FK (62.60%), RUSBoost (72.60%), as well as BAS (84.90%) indicates that ESOA (96.27%) outperforms the other algorithms in terms of Accuracy (ACC), Sensitivity (SEN), Precision (PREC), and Area Under the Curve (AUC) metrics. To our knowledge, this is the highest fraud detection accuracy reported in the existing literature. Journal Article Expert Systems with Applications 231 120760 Elsevier BV 0957-4174 30 11 2023 2023-11-30 10.1016/j.eswa.2023.120760 http://dx.doi.org/10.1016/j.eswa.2023.120760 COLLEGE NANME Science and Engineering - Faculty COLLEGE CODE FGSEN Swansea University This paper is partially supported by National Natural Science Foundation of China with grant number 72271109 2023-09-04T12:42:10.0308232 2023-06-13T14:20:10.8761894 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Electronic and Electrical Engineering Ziwei Yi 1 Xinwei Cao 2 Xujin Pu 3 Yiding Wu 4 Zuyan Chen 5 Ameer Tamoor Khan 6 Adam Francis 7 Shuai Li 8
title Fraud detection in capital markets: A novel machine learning approach
spellingShingle Fraud detection in capital markets: A novel machine learning approach
Adam Francis
title_short Fraud detection in capital markets: A novel machine learning approach
title_full Fraud detection in capital markets: A novel machine learning approach
title_fullStr Fraud detection in capital markets: A novel machine learning approach
title_full_unstemmed Fraud detection in capital markets: A novel machine learning approach
title_sort Fraud detection in capital markets: A novel machine learning approach
author_id_str_mv 8449248c17fec32f131097c0d1a768cc
author_id_fullname_str_mv 8449248c17fec32f131097c0d1a768cc_***_Adam Francis
author Adam Francis
author2 Ziwei Yi
Xinwei Cao
Xujin Pu
Yiding Wu
Zuyan Chen
Ameer Tamoor Khan
Adam Francis
Shuai Li
format Journal article
container_title Expert Systems with Applications
container_volume 231
container_start_page 120760
publishDate 2023
institution Swansea University
issn 0957-4174
doi_str_mv 10.1016/j.eswa.2023.120760
publisher Elsevier BV
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Electronic and Electrical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Electronic and Electrical Engineering
url http://dx.doi.org/10.1016/j.eswa.2023.120760
document_store_str 0
active_str 0
description Traditional auditing methods require collating massive amounts of financial indicators and related transaction data, which can be labor-intensive. Typical machine learning models are relatively weak for imbalanced data, and this work aims to focus on a novel approach to fraud detection. This paper presents a fraud detection framework via adopting a machine learning method integrated with a recently proposed meta-heuristics algorithm Egret Swarm Optimization Algorithm (ESOA). A cost-sensitive objective function and loss function were then constructed, and a non-linear model was used to map the predicted values into the labels of 0 (non-fraud) and 1 (fraud). In the experiment section, an AAER benchmark dataset collected by the UCB’s Center for Financial Reporting and Management is utilized to verify the performance of the proposed approach. A detailed comparison with recently proposed state-of-the-art algorithms such as Logit (67.20%), SVM-FK (62.60%), RUSBoost (72.60%), as well as BAS (84.90%) indicates that ESOA (96.27%) outperforms the other algorithms in terms of Accuracy (ACC), Sensitivity (SEN), Precision (PREC), and Area Under the Curve (AUC) metrics. To our knowledge, this is the highest fraud detection accuracy reported in the existing literature.
published_date 2023-11-30T12:42:12Z
_version_ 1776107107985129472
score 11.012947

Similar Items