Machine Learning Based on Resampling Approaches and Deep Reinforcement Learning for Credit Card Fraud Detection Systems

The problem of imbalanced datasets is a significant concern when creating reliable credit card fraud (CCF) detection systems. In this work, we study and evaluate recent advances in machine learning (ML) algorithms and deep reinforcement learning (DRL) used for CCF detection systems, including fraud...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Tran Khanh Dang, Thanh Cong Tran, Luc Minh Tuan, Mai Viet Tiep
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	machine learning deep reinforcement learning classification imbalanced data credit card fraud resampling techniques Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/7d123f64ba5242b6826b8c4558a006d3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7d123f64ba5242b6826b8c4558a006d3
record_format	dspace
spelling	oai:doaj.org-article:7d123f64ba5242b6826b8c4558a006d32021-11-11T15:06:18ZMachine Learning Based on Resampling Approaches and Deep Reinforcement Learning for Credit Card Fraud Detection Systems10.3390/app1121100042076-3417https://doaj.org/article/7d123f64ba5242b6826b8c4558a006d32021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10004https://doaj.org/toc/2076-3417The problem of imbalanced datasets is a significant concern when creating reliable credit card fraud (CCF) detection systems. In this work, we study and evaluate recent advances in machine learning (ML) algorithms and deep reinforcement learning (DRL) used for CCF detection systems, including fraud and non-fraud labels. Based on two resampling approaches, SMOTE and ADASYN are used to resample the imbalanced CCF dataset. ML algorithms are, then, applied to this balanced dataset to establish CCF detection systems. Next, DRL is employed to create detection systems based on the imbalanced CCF dataset. The diverse classification metrics are indicated to thoroughly evaluate the performance of these ML and DRL models. Through empirical experiments, we identify the reliable degree of ML models based on two resampling approaches and DRL models for CCF detection. When SMOTE and ADASYN are used to resampling original CCF datasets before training/test split, the ML models show very high outcomes of above 99% accuracy. However, when these techniques are employed to resample for only the training CCF datasets, these ML models show lower results, particularly in terms of logistic regression with 1.81% precision and 3.55% F1 score for using ADASYN. Our work reveals the DRL model is ineffective and achieves low performance, with only 34.8% accuracy.Tran Khanh DangThanh Cong TranLuc Minh TuanMai Viet TiepMDPI AGarticlemachine learningdeep reinforcement learningclassificationimbalanced datacredit card fraudresampling techniquesTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10004, p 10004 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	machine learning deep reinforcement learning classification imbalanced data credit card fraud resampling techniques Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	machine learning deep reinforcement learning classification imbalanced data credit card fraud resampling techniques Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Tran Khanh Dang Thanh Cong Tran Luc Minh Tuan Mai Viet Tiep Machine Learning Based on Resampling Approaches and Deep Reinforcement Learning for Credit Card Fraud Detection Systems
description	The problem of imbalanced datasets is a significant concern when creating reliable credit card fraud (CCF) detection systems. In this work, we study and evaluate recent advances in machine learning (ML) algorithms and deep reinforcement learning (DRL) used for CCF detection systems, including fraud and non-fraud labels. Based on two resampling approaches, SMOTE and ADASYN are used to resample the imbalanced CCF dataset. ML algorithms are, then, applied to this balanced dataset to establish CCF detection systems. Next, DRL is employed to create detection systems based on the imbalanced CCF dataset. The diverse classification metrics are indicated to thoroughly evaluate the performance of these ML and DRL models. Through empirical experiments, we identify the reliable degree of ML models based on two resampling approaches and DRL models for CCF detection. When SMOTE and ADASYN are used to resampling original CCF datasets before training/test split, the ML models show very high outcomes of above 99% accuracy. However, when these techniques are employed to resample for only the training CCF datasets, these ML models show lower results, particularly in terms of logistic regression with 1.81% precision and 3.55% F1 score for using ADASYN. Our work reveals the DRL model is ineffective and achieves low performance, with only 34.8% accuracy.
format	article
author	Tran Khanh Dang Thanh Cong Tran Luc Minh Tuan Mai Viet Tiep
author_facet	Tran Khanh Dang Thanh Cong Tran Luc Minh Tuan Mai Viet Tiep
author_sort	Tran Khanh Dang
title	Machine Learning Based on Resampling Approaches and Deep Reinforcement Learning for Credit Card Fraud Detection Systems
title_short	Machine Learning Based on Resampling Approaches and Deep Reinforcement Learning for Credit Card Fraud Detection Systems
title_full	Machine Learning Based on Resampling Approaches and Deep Reinforcement Learning for Credit Card Fraud Detection Systems
title_fullStr	Machine Learning Based on Resampling Approaches and Deep Reinforcement Learning for Credit Card Fraud Detection Systems
title_full_unstemmed	Machine Learning Based on Resampling Approaches and Deep Reinforcement Learning for Credit Card Fraud Detection Systems
title_sort	machine learning based on resampling approaches and deep reinforcement learning for credit card fraud detection systems
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/7d123f64ba5242b6826b8c4558a006d3
work_keys_str_mv	AT trankhanhdang machinelearningbasedonresamplingapproachesanddeepreinforcementlearningforcreditcardfrauddetectionsystems AT thanhcongtran machinelearningbasedonresamplingapproachesanddeepreinforcementlearningforcreditcardfrauddetectionsystems AT lucminhtuan machinelearningbasedonresamplingapproachesanddeepreinforcementlearningforcreditcardfrauddetectionsystems AT maiviettiep machinelearningbasedonresamplingapproachesanddeepreinforcementlearningforcreditcardfrauddetectionsystems
_version_	1718437152787791872

Machine Learning Based on Resampling Approaches and Deep Reinforcement Learning for Credit Card Fraud Detection Systems

Ejemplares similares