Enhanced credit card fraud detection based on attention mechanism and LSTM deep model

Abstract As credit card becomes the most popular payment mode particularly in the online sector, the fraudulent activities using credit card payment technologies are rapidly increasing as a result. For this end, it is obligatory for financial institutions to continuously improve their fraud detectio...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ibtissam Benchaji, Samira Douzi, Bouabid El Ouahidi, Jaafar Jaafari
Formato:	article
Lenguaje:	EN
Publicado:	SpringerOpen 2021
Materias:	Deep learning Attention mechanism Fraud detection Sequence learning Recurrent neural networks LSTM Computer engineering. Computer hardware TK7885-7895 Information technology T58.5-58.64 Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/fa46521e21ee4a728bf0dea16cbc2bce
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fa46521e21ee4a728bf0dea16cbc2bce
record_format	dspace
spelling	oai:doaj.org-article:fa46521e21ee4a728bf0dea16cbc2bce2021-12-05T12:03:20ZEnhanced credit card fraud detection based on attention mechanism and LSTM deep model10.1186/s40537-021-00541-82196-1115https://doaj.org/article/fa46521e21ee4a728bf0dea16cbc2bce2021-12-01T00:00:00Zhttps://doi.org/10.1186/s40537-021-00541-8https://doaj.org/toc/2196-1115Abstract As credit card becomes the most popular payment mode particularly in the online sector, the fraudulent activities using credit card payment technologies are rapidly increasing as a result. For this end, it is obligatory for financial institutions to continuously improve their fraud detection systems to reduce huge losses. The purpose of this paper is to develop a novel system for credit card fraud detection based on sequential modeling of data, using attention mechanism and LSTM deep recurrent neural networks. The proposed model, compared to previous studies, considers the sequential nature of transactional data and allows the classifier to identify the most important transactions in the input sequence that predict at higher accuracy fraudulent transactions. Precisely, the robustness of our model is built by combining the strength of three sub-methods; the uniform manifold approximation and projection (UMAP) for selecting the most useful predictive features, the Long Short Term Memory (LSTM) networks for incorporating transaction sequences and the attention mechanism to enhance LSTM performances. The experimentations of our model give strong results in terms of efficiency and effectiveness.Ibtissam BenchajiSamira DouziBouabid El OuahidiJaafar JaafariSpringerOpenarticleDeep learningAttention mechanismFraud detectionSequence learningRecurrent neural networksLSTMComputer engineering. Computer hardwareTK7885-7895Information technologyT58.5-58.64Electronic computers. Computer scienceQA75.5-76.95ENJournal of Big Data, Vol 8, Iss 1, Pp 1-21 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Deep learning Attention mechanism Fraud detection Sequence learning Recurrent neural networks LSTM Computer engineering. Computer hardware TK7885-7895 Information technology T58.5-58.64 Electronic computers. Computer science QA75.5-76.95
spellingShingle	Deep learning Attention mechanism Fraud detection Sequence learning Recurrent neural networks LSTM Computer engineering. Computer hardware TK7885-7895 Information technology T58.5-58.64 Electronic computers. Computer science QA75.5-76.95 Ibtissam Benchaji Samira Douzi Bouabid El Ouahidi Jaafar Jaafari Enhanced credit card fraud detection based on attention mechanism and LSTM deep model
description	Abstract As credit card becomes the most popular payment mode particularly in the online sector, the fraudulent activities using credit card payment technologies are rapidly increasing as a result. For this end, it is obligatory for financial institutions to continuously improve their fraud detection systems to reduce huge losses. The purpose of this paper is to develop a novel system for credit card fraud detection based on sequential modeling of data, using attention mechanism and LSTM deep recurrent neural networks. The proposed model, compared to previous studies, considers the sequential nature of transactional data and allows the classifier to identify the most important transactions in the input sequence that predict at higher accuracy fraudulent transactions. Precisely, the robustness of our model is built by combining the strength of three sub-methods; the uniform manifold approximation and projection (UMAP) for selecting the most useful predictive features, the Long Short Term Memory (LSTM) networks for incorporating transaction sequences and the attention mechanism to enhance LSTM performances. The experimentations of our model give strong results in terms of efficiency and effectiveness.
format	article
author	Ibtissam Benchaji Samira Douzi Bouabid El Ouahidi Jaafar Jaafari
author_facet	Ibtissam Benchaji Samira Douzi Bouabid El Ouahidi Jaafar Jaafari
author_sort	Ibtissam Benchaji
title	Enhanced credit card fraud detection based on attention mechanism and LSTM deep model
title_short	Enhanced credit card fraud detection based on attention mechanism and LSTM deep model
title_full	Enhanced credit card fraud detection based on attention mechanism and LSTM deep model
title_fullStr	Enhanced credit card fraud detection based on attention mechanism and LSTM deep model
title_full_unstemmed	Enhanced credit card fraud detection based on attention mechanism and LSTM deep model
title_sort	enhanced credit card fraud detection based on attention mechanism and lstm deep model
publisher	SpringerOpen
publishDate	2021
url	https://doaj.org/article/fa46521e21ee4a728bf0dea16cbc2bce
work_keys_str_mv	AT ibtissambenchaji enhancedcreditcardfrauddetectionbasedonattentionmechanismandlstmdeepmodel AT samiradouzi enhancedcreditcardfrauddetectionbasedonattentionmechanismandlstmdeepmodel AT bouabidelouahidi enhancedcreditcardfrauddetectionbasedonattentionmechanismandlstmdeepmodel AT jaafarjaafari enhancedcreditcardfrauddetectionbasedonattentionmechanismandlstmdeepmodel
_version_	1718372354550136832

Enhanced credit card fraud detection based on attention mechanism and LSTM deep model

Ejemplares similares