Detecting Fraudulent Transactions Using Stacked Autoencoder Kernel ELM Optimized by the Dandelion Algorithm

The risk of fraudulent activity has significantly increased with the rise in digital payments. To resolve this issue there is a need for reliable real-time fraud detection technologies. This research introduced an innovative method called stacked autoencoder kernel extreme learning machine optimized...

Full description

Bibliographic Details
Main Authors: Fatima Zohra El Hlouli, Jamal Riffi, Mhamed Sayyouri, Mohamed Adnane Mahraz, Ali Yahyaouy, Khalid El Fazazy, Hamid Tairi
Format: Article
Language:English
Published: MDPI AG 2023-11-01
Series:Journal of Theoretical and Applied Electronic Commerce Research
Subjects:
Online Access:https://www.mdpi.com/0718-1876/18/4/103
_version_ 1827574412421890048
author Fatima Zohra El Hlouli
Jamal Riffi
Mhamed Sayyouri
Mohamed Adnane Mahraz
Ali Yahyaouy
Khalid El Fazazy
Hamid Tairi
author_facet Fatima Zohra El Hlouli
Jamal Riffi
Mhamed Sayyouri
Mohamed Adnane Mahraz
Ali Yahyaouy
Khalid El Fazazy
Hamid Tairi
author_sort Fatima Zohra El Hlouli
collection DOAJ
description The risk of fraudulent activity has significantly increased with the rise in digital payments. To resolve this issue there is a need for reliable real-time fraud detection technologies. This research introduced an innovative method called stacked autoencoder kernel extreme learning machine optimized by the dandelion algorithm (S-AEKELM-DA) to detect fraudulent transactions. The primary objective was to enhance the kernel extreme learning machine (KELM) performance by integrating the dandelion technique into a stacked autoencoder kernel ELM architecture. This study aimed to improve the overall effectiveness of the proposed method in fraud detection by optimizing the regularization parameter (c) and the kernel parameter (σ). To evaluate the S-AEKELM-DA approach; simulations and experiments were conducted using four credit card datasets. The results demonstrated remarkable performance, with our method achieving high accuracy, recall, precision, and F1-score in real time for detecting fraudulent transactions. These findings highlight the effectiveness and reliability of the suggested approach. By incorporating the dandelion algorithm into the S-AEKELM framework, this research advances fraud detection capabilities, thus ensuring the security of digital transactions.
first_indexed 2024-03-08T20:36:44Z
format Article
id doaj.art-4dc4d43a188f498cbc2c68ed2af86398
institution Directory Open Access Journal
issn 0718-1876
language English
last_indexed 2024-03-08T20:36:44Z
publishDate 2023-11-01
publisher MDPI AG
record_format Article
series Journal of Theoretical and Applied Electronic Commerce Research
spelling doaj.art-4dc4d43a188f498cbc2c68ed2af863982023-12-22T14:20:12ZengMDPI AGJournal of Theoretical and Applied Electronic Commerce Research0718-18762023-11-011842057207610.3390/jtaer18040103Detecting Fraudulent Transactions Using Stacked Autoencoder Kernel ELM Optimized by the Dandelion AlgorithmFatima Zohra El Hlouli0Jamal Riffi1Mhamed Sayyouri2Mohamed Adnane Mahraz3Ali Yahyaouy4Khalid El Fazazy5Hamid Tairi6LISAC Laboratory, Faculty of Sciences, University Sidi Mohamed Ben Abdellah, Fes Atlas 30003, MoroccoLISAC Laboratory, Faculty of Sciences, University Sidi Mohamed Ben Abdellah, Fes Atlas 30003, MoroccoLISA Laboratory, National School of Applied Sciences, University Sidi Mohamed Ben Abdellah, Fes Atlas 30003, MoroccoLISAC Laboratory, Faculty of Sciences, University Sidi Mohamed Ben Abdellah, Fes Atlas 30003, MoroccoLISAC Laboratory, Faculty of Sciences, University Sidi Mohamed Ben Abdellah, Fes Atlas 30003, MoroccoLISAC Laboratory, Faculty of Sciences, University Sidi Mohamed Ben Abdellah, Fes Atlas 30003, MoroccoLISAC Laboratory, Faculty of Sciences, University Sidi Mohamed Ben Abdellah, Fes Atlas 30003, MoroccoThe risk of fraudulent activity has significantly increased with the rise in digital payments. To resolve this issue there is a need for reliable real-time fraud detection technologies. This research introduced an innovative method called stacked autoencoder kernel extreme learning machine optimized by the dandelion algorithm (S-AEKELM-DA) to detect fraudulent transactions. The primary objective was to enhance the kernel extreme learning machine (KELM) performance by integrating the dandelion technique into a stacked autoencoder kernel ELM architecture. This study aimed to improve the overall effectiveness of the proposed method in fraud detection by optimizing the regularization parameter (c) and the kernel parameter (σ). To evaluate the S-AEKELM-DA approach; simulations and experiments were conducted using four credit card datasets. The results demonstrated remarkable performance, with our method achieving high accuracy, recall, precision, and F1-score in real time for detecting fraudulent transactions. These findings highlight the effectiveness and reliability of the suggested approach. By incorporating the dandelion algorithm into the S-AEKELM framework, this research advances fraud detection capabilities, thus ensuring the security of digital transactions.https://www.mdpi.com/0718-1876/18/4/103kernel extreme learning machinestacked autoencoderdandelion algorithmcredit card fraud
spellingShingle Fatima Zohra El Hlouli
Jamal Riffi
Mhamed Sayyouri
Mohamed Adnane Mahraz
Ali Yahyaouy
Khalid El Fazazy
Hamid Tairi
Detecting Fraudulent Transactions Using Stacked Autoencoder Kernel ELM Optimized by the Dandelion Algorithm
Journal of Theoretical and Applied Electronic Commerce Research
kernel extreme learning machine
stacked autoencoder
dandelion algorithm
credit card fraud
title Detecting Fraudulent Transactions Using Stacked Autoencoder Kernel ELM Optimized by the Dandelion Algorithm
title_full Detecting Fraudulent Transactions Using Stacked Autoencoder Kernel ELM Optimized by the Dandelion Algorithm
title_fullStr Detecting Fraudulent Transactions Using Stacked Autoencoder Kernel ELM Optimized by the Dandelion Algorithm
title_full_unstemmed Detecting Fraudulent Transactions Using Stacked Autoencoder Kernel ELM Optimized by the Dandelion Algorithm
title_short Detecting Fraudulent Transactions Using Stacked Autoencoder Kernel ELM Optimized by the Dandelion Algorithm
title_sort detecting fraudulent transactions using stacked autoencoder kernel elm optimized by the dandelion algorithm
topic kernel extreme learning machine
stacked autoencoder
dandelion algorithm
credit card fraud
url https://www.mdpi.com/0718-1876/18/4/103
work_keys_str_mv AT fatimazohraelhlouli detectingfraudulenttransactionsusingstackedautoencoderkernelelmoptimizedbythedandelionalgorithm
AT jamalriffi detectingfraudulenttransactionsusingstackedautoencoderkernelelmoptimizedbythedandelionalgorithm
AT mhamedsayyouri detectingfraudulenttransactionsusingstackedautoencoderkernelelmoptimizedbythedandelionalgorithm
AT mohamedadnanemahraz detectingfraudulenttransactionsusingstackedautoencoderkernelelmoptimizedbythedandelionalgorithm
AT aliyahyaouy detectingfraudulenttransactionsusingstackedautoencoderkernelelmoptimizedbythedandelionalgorithm
AT khalidelfazazy detectingfraudulenttransactionsusingstackedautoencoderkernelelmoptimizedbythedandelionalgorithm
AT hamidtairi detectingfraudulenttransactionsusingstackedautoencoderkernelelmoptimizedbythedandelionalgorithm