Loading…

Multi-Class Mobile Money Service Financial Fraud Detection by Integrating Supervised Learning with Adversarial Autoencoders

Given the actual volume and speed of financial transactions, financial fraud detection systems are constantly evolving based on new computational intelligence algorithms. Therefore, transaction monitoring and analysis prevent monetary losses caused by fraudsters. Since the fraud detection process is...

Full description

Saved in:
Bibliographic Details
Main Authors: Silva, Julio Cezar Soares, Macedo, David, Zanchettin, Cleber, Oliveira, Adriano L.I., de Almeida Filho, Adiel Teixeira
Format: Conference Proceeding
Language:English
Subjects:
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 7
container_issue
container_start_page 1
container_title
container_volume
creator Silva, Julio Cezar Soares
Macedo, David
Zanchettin, Cleber
Oliveira, Adriano L.I.
de Almeida Filho, Adiel Teixeira
description Given the actual volume and speed of financial transactions, financial fraud detection systems are constantly evolving based on new computational intelligence algorithms. Therefore, transaction monitoring and analysis prevent monetary losses caused by fraudsters. Since the fraud detection process is a labor-intensive task for human auditors given the huge amount of daily transactions processed by financial services information systems. Credit card is the financial product most explored in the financial fraud detection literature, while mobile money service is becoming a popular option for payments, fraud detection for such financial product has not yet been deeply explored. Therefore, it is interesting to optimize the auditing process and test new quantitative techniques, such as deep learning, to support human auditors before double-checking a suspicious transaction. Thus, we propose an integration of adversarial autoencoders and machine learning methods to perform an objective classification among three transaction types: regular, local, and global anomaly. The integration consists of using the autoencoder's generated latent vectors as features for the supervised learning algorithms. The experiments considered different latent vector space forms concerning their dimensionality and the clusters generated by a prior Gaussian mixture. The results show that some classifiers may accept latent characteristics well, getting better or similar performance when using all the original characteristics.
doi_str_mv 10.1109/IJCNN52387.2021.9533313
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_9533313</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9533313</ieee_id><sourcerecordid>9533313</sourcerecordid><originalsourceid>FETCH-LOGICAL-i203t-7fe243740038a2941eee61107821252d1f0d9ae3ad060a714010a67bd85afa953</originalsourceid><addsrcrecordid>eNotkMtOwzAURA0SEm3hC1jgH0i5tvPysgoUgtqyKKyr2_imGAWncpyiip8nFV2NdKQz0gxj9wKmQoB-KF-L1SqRKs-mEqSY6kQpJdQFG4s0TWKlAfQlG0mRiiiOIbtm4677ApBKazViv8u-CTYqGuw6vmy3tqEhHB35mvzBVsTn1qGrLDZ87rE3_JECVcG2jm-PvHSBdh6DdTu-7vcnpSPDF4TendiPDZ98Zg7kO_SnjlkfWnJVawZyw65qbDq6PeeEfcyf3ouXaPH2XBazRWQlqBBlNclYZTGAylHqWBBROmzPcilkIo2owWgkhQZSwEzEIADTbGvyBGsc_piwu_9eO5ibvbff6I-b81HqD_svX0c</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Multi-Class Mobile Money Service Financial Fraud Detection by Integrating Supervised Learning with Adversarial Autoencoders</title><source>IEEE Xplore All Conference Series</source><creator>Silva, Julio Cezar Soares ; Macedo, David ; Zanchettin, Cleber ; Oliveira, Adriano L.I. ; de Almeida Filho, Adiel Teixeira</creator><creatorcontrib>Silva, Julio Cezar Soares ; Macedo, David ; Zanchettin, Cleber ; Oliveira, Adriano L.I. ; de Almeida Filho, Adiel Teixeira</creatorcontrib><description>Given the actual volume and speed of financial transactions, financial fraud detection systems are constantly evolving based on new computational intelligence algorithms. Therefore, transaction monitoring and analysis prevent monetary losses caused by fraudsters. Since the fraud detection process is a labor-intensive task for human auditors given the huge amount of daily transactions processed by financial services information systems. Credit card is the financial product most explored in the financial fraud detection literature, while mobile money service is becoming a popular option for payments, fraud detection for such financial product has not yet been deeply explored. Therefore, it is interesting to optimize the auditing process and test new quantitative techniques, such as deep learning, to support human auditors before double-checking a suspicious transaction. Thus, we propose an integration of adversarial autoencoders and machine learning methods to perform an objective classification among three transaction types: regular, local, and global anomaly. The integration consists of using the autoencoder's generated latent vectors as features for the supervised learning algorithms. The experiments considered different latent vector space forms concerning their dimensionality and the clusters generated by a prior Gaussian mixture. The results show that some classifiers may accept latent characteristics well, getting better or similar performance when using all the original characteristics.</description><identifier>EISSN: 2161-4407</identifier><identifier>EISBN: 1665439009</identifier><identifier>EISBN: 9781665439008</identifier><identifier>DOI: 10.1109/IJCNN52387.2021.9533313</identifier><language>eng</language><publisher>IEEE</publisher><subject>adversarial autoencoders ; Deep learning ; Feature extraction ; fraud detection ; Machine learning algorithms ; multi-class imbalanced ; Neural networks ; Radio frequency ; Supervised learning ; Task analysis</subject><ispartof>2021 International Joint Conference on Neural Networks (IJCNN), 2021, p.1-7</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9533313$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,23930,23931,25140,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9533313$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Silva, Julio Cezar Soares</creatorcontrib><creatorcontrib>Macedo, David</creatorcontrib><creatorcontrib>Zanchettin, Cleber</creatorcontrib><creatorcontrib>Oliveira, Adriano L.I.</creatorcontrib><creatorcontrib>de Almeida Filho, Adiel Teixeira</creatorcontrib><title>Multi-Class Mobile Money Service Financial Fraud Detection by Integrating Supervised Learning with Adversarial Autoencoders</title><title>2021 International Joint Conference on Neural Networks (IJCNN)</title><addtitle>IJCNN</addtitle><description>Given the actual volume and speed of financial transactions, financial fraud detection systems are constantly evolving based on new computational intelligence algorithms. Therefore, transaction monitoring and analysis prevent monetary losses caused by fraudsters. Since the fraud detection process is a labor-intensive task for human auditors given the huge amount of daily transactions processed by financial services information systems. Credit card is the financial product most explored in the financial fraud detection literature, while mobile money service is becoming a popular option for payments, fraud detection for such financial product has not yet been deeply explored. Therefore, it is interesting to optimize the auditing process and test new quantitative techniques, such as deep learning, to support human auditors before double-checking a suspicious transaction. Thus, we propose an integration of adversarial autoencoders and machine learning methods to perform an objective classification among three transaction types: regular, local, and global anomaly. The integration consists of using the autoencoder's generated latent vectors as features for the supervised learning algorithms. The experiments considered different latent vector space forms concerning their dimensionality and the clusters generated by a prior Gaussian mixture. The results show that some classifiers may accept latent characteristics well, getting better or similar performance when using all the original characteristics.</description><subject>adversarial autoencoders</subject><subject>Deep learning</subject><subject>Feature extraction</subject><subject>fraud detection</subject><subject>Machine learning algorithms</subject><subject>multi-class imbalanced</subject><subject>Neural networks</subject><subject>Radio frequency</subject><subject>Supervised learning</subject><subject>Task analysis</subject><issn>2161-4407</issn><isbn>1665439009</isbn><isbn>9781665439008</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2021</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotkMtOwzAURA0SEm3hC1jgH0i5tvPysgoUgtqyKKyr2_imGAWncpyiip8nFV2NdKQz0gxj9wKmQoB-KF-L1SqRKs-mEqSY6kQpJdQFG4s0TWKlAfQlG0mRiiiOIbtm4677ApBKazViv8u-CTYqGuw6vmy3tqEhHB35mvzBVsTn1qGrLDZ87rE3_JECVcG2jm-PvHSBdh6DdTu-7vcnpSPDF4TendiPDZ98Zg7kO_SnjlkfWnJVawZyw65qbDq6PeeEfcyf3ouXaPH2XBazRWQlqBBlNclYZTGAylHqWBBROmzPcilkIo2owWgkhQZSwEzEIADTbGvyBGsc_piwu_9eO5ibvbff6I-b81HqD_svX0c</recordid><startdate>20210718</startdate><enddate>20210718</enddate><creator>Silva, Julio Cezar Soares</creator><creator>Macedo, David</creator><creator>Zanchettin, Cleber</creator><creator>Oliveira, Adriano L.I.</creator><creator>de Almeida Filho, Adiel Teixeira</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>20210718</creationdate><title>Multi-Class Mobile Money Service Financial Fraud Detection by Integrating Supervised Learning with Adversarial Autoencoders</title><author>Silva, Julio Cezar Soares ; Macedo, David ; Zanchettin, Cleber ; Oliveira, Adriano L.I. ; de Almeida Filho, Adiel Teixeira</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i203t-7fe243740038a2941eee61107821252d1f0d9ae3ad060a714010a67bd85afa953</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2021</creationdate><topic>adversarial autoencoders</topic><topic>Deep learning</topic><topic>Feature extraction</topic><topic>fraud detection</topic><topic>Machine learning algorithms</topic><topic>multi-class imbalanced</topic><topic>Neural networks</topic><topic>Radio frequency</topic><topic>Supervised learning</topic><topic>Task analysis</topic><toplevel>online_resources</toplevel><creatorcontrib>Silva, Julio Cezar Soares</creatorcontrib><creatorcontrib>Macedo, David</creatorcontrib><creatorcontrib>Zanchettin, Cleber</creatorcontrib><creatorcontrib>Oliveira, Adriano L.I.</creatorcontrib><creatorcontrib>de Almeida Filho, Adiel Teixeira</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library Online</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Silva, Julio Cezar Soares</au><au>Macedo, David</au><au>Zanchettin, Cleber</au><au>Oliveira, Adriano L.I.</au><au>de Almeida Filho, Adiel Teixeira</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Multi-Class Mobile Money Service Financial Fraud Detection by Integrating Supervised Learning with Adversarial Autoencoders</atitle><btitle>2021 International Joint Conference on Neural Networks (IJCNN)</btitle><stitle>IJCNN</stitle><date>2021-07-18</date><risdate>2021</risdate><spage>1</spage><epage>7</epage><pages>1-7</pages><eissn>2161-4407</eissn><eisbn>1665439009</eisbn><eisbn>9781665439008</eisbn><abstract>Given the actual volume and speed of financial transactions, financial fraud detection systems are constantly evolving based on new computational intelligence algorithms. Therefore, transaction monitoring and analysis prevent monetary losses caused by fraudsters. Since the fraud detection process is a labor-intensive task for human auditors given the huge amount of daily transactions processed by financial services information systems. Credit card is the financial product most explored in the financial fraud detection literature, while mobile money service is becoming a popular option for payments, fraud detection for such financial product has not yet been deeply explored. Therefore, it is interesting to optimize the auditing process and test new quantitative techniques, such as deep learning, to support human auditors before double-checking a suspicious transaction. Thus, we propose an integration of adversarial autoencoders and machine learning methods to perform an objective classification among three transaction types: regular, local, and global anomaly. The integration consists of using the autoencoder's generated latent vectors as features for the supervised learning algorithms. The experiments considered different latent vector space forms concerning their dimensionality and the clusters generated by a prior Gaussian mixture. The results show that some classifiers may accept latent characteristics well, getting better or similar performance when using all the original characteristics.</abstract><pub>IEEE</pub><doi>10.1109/IJCNN52387.2021.9533313</doi><tpages>7</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2161-4407
ispartof 2021 International Joint Conference on Neural Networks (IJCNN), 2021, p.1-7
issn 2161-4407
language eng
recordid cdi_ieee_primary_9533313
source IEEE Xplore All Conference Series
subjects adversarial autoencoders
Deep learning
Feature extraction
fraud detection
Machine learning algorithms
multi-class imbalanced
Neural networks
Radio frequency
Supervised learning
Task analysis
title Multi-Class Mobile Money Service Financial Fraud Detection by Integrating Supervised Learning with Adversarial Autoencoders
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T07%3A06%3A44IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Multi-Class%20Mobile%20Money%20Service%20Financial%20Fraud%20Detection%20by%20Integrating%20Supervised%20Learning%20with%20Adversarial%20Autoencoders&rft.btitle=2021%20International%20Joint%20Conference%20on%20Neural%20Networks%20(IJCNN)&rft.au=Silva,%20Julio%20Cezar%20Soares&rft.date=2021-07-18&rft.spage=1&rft.epage=7&rft.pages=1-7&rft.eissn=2161-4407&rft_id=info:doi/10.1109/IJCNN52387.2021.9533313&rft.eisbn=1665439009&rft.eisbn_list=9781665439008&rft_dat=%3Cieee_CHZPO%3E9533313%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i203t-7fe243740038a2941eee61107821252d1f0d9ae3ad060a714010a67bd85afa953%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=9533313&rfr_iscdi=true