Abnormal Detection of Cash-Out Groups in IoT Based Payment

With the rise of online/mobile transactions, the cost of cash-out has decreased and the cost of detection has increased. In the world of online/mobile payment in IoT, merchants and credit cards can be applied and approved online and used in the form of a QR code but not a physical card or Point of S...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hao Zhou, Ming Zhang, Lei Pang, Jian-Hua Li
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	credit card transactions cash-out group Internet of Things (IoT) graph embedding partial graph clustering clustering Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/a699ca26d2864046901fb29b2e5fda32
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a699ca26d2864046901fb29b2e5fda32
record_format	dspace
spelling	oai:doaj.org-article:a699ca26d2864046901fb29b2e5fda322021-11-25T18:56:59ZAbnormal Detection of Cash-Out Groups in IoT Based Payment10.3390/s212275071424-8220https://doaj.org/article/a699ca26d2864046901fb29b2e5fda322021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7507https://doaj.org/toc/1424-8220With the rise of online/mobile transactions, the cost of cash-out has decreased and the cost of detection has increased. In the world of online/mobile payment in IoT, merchants and credit cards can be applied and approved online and used in the form of a QR code but not a physical card or Point of Sale equipment, making it easy for these systems to be controlled by a group of fraudsters. In mainland China, where the credit card transaction fee is, on average, lower than a retail loan rate, the credit card cash-out option is attractive for people for an investment or business operation, which, after investigation, can be considered unlawful if over a certain amount is used. Because cash-out will incur fees for the merchants, while bringing money to the credit cards’ owners, it is difficult to confirm, as nobody will declare or admit it. Furthermore, it is more difficult to detect cash-out groups than individuals, because cash-out groups are more hidden, which leads to bigger transaction amounts. We propose a new method for the detection of cash-out groups. First, the seed cards are mined and the seed cards’ diffusion is then performed through the local graph clustering algorithm (Approximate PageRank, APR). Second, a merchant association network in IoT is constructed based on the suspicious cards, using the graph embedding algorithm (Node2Vec). Third, we use the clustering algorithm (DBSCAN) to cluster the nodes in the Euclidean space, which divides the merchants into groups. Finally, we design a method to classify the severity of the groups to facilitate the following risk investigation. The proposed method covers 145 merchants from 195 known risky merchants in groups that acquire cash-out from four banks, which shows that this method can identify most (74.4%) cash-out groups. In addition, the proposed method identifies a further 178 cash-out merchants in the group within the same four acquirers, resulting in a total of 30,586 merchants. The results and framework are already adopted and absorbed into the design for a cash-out group detection system in IoT by the Chinese payment processor.Hao ZhouMing ZhangLei PangJian-Hua LiMDPI AGarticlecredit card transactionscash-out groupInternet of Things (IoT)graph embeddingpartial graph clusteringclusteringChemical technologyTP1-1185ENSensors, Vol 21, Iss 7507, p 7507 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	credit card transactions cash-out group Internet of Things (IoT) graph embedding partial graph clustering clustering Chemical technology TP1-1185
spellingShingle	credit card transactions cash-out group Internet of Things (IoT) graph embedding partial graph clustering clustering Chemical technology TP1-1185 Hao Zhou Ming Zhang Lei Pang Jian-Hua Li Abnormal Detection of Cash-Out Groups in IoT Based Payment
description	With the rise of online/mobile transactions, the cost of cash-out has decreased and the cost of detection has increased. In the world of online/mobile payment in IoT, merchants and credit cards can be applied and approved online and used in the form of a QR code but not a physical card or Point of Sale equipment, making it easy for these systems to be controlled by a group of fraudsters. In mainland China, where the credit card transaction fee is, on average, lower than a retail loan rate, the credit card cash-out option is attractive for people for an investment or business operation, which, after investigation, can be considered unlawful if over a certain amount is used. Because cash-out will incur fees for the merchants, while bringing money to the credit cards’ owners, it is difficult to confirm, as nobody will declare or admit it. Furthermore, it is more difficult to detect cash-out groups than individuals, because cash-out groups are more hidden, which leads to bigger transaction amounts. We propose a new method for the detection of cash-out groups. First, the seed cards are mined and the seed cards’ diffusion is then performed through the local graph clustering algorithm (Approximate PageRank, APR). Second, a merchant association network in IoT is constructed based on the suspicious cards, using the graph embedding algorithm (Node2Vec). Third, we use the clustering algorithm (DBSCAN) to cluster the nodes in the Euclidean space, which divides the merchants into groups. Finally, we design a method to classify the severity of the groups to facilitate the following risk investigation. The proposed method covers 145 merchants from 195 known risky merchants in groups that acquire cash-out from four banks, which shows that this method can identify most (74.4%) cash-out groups. In addition, the proposed method identifies a further 178 cash-out merchants in the group within the same four acquirers, resulting in a total of 30,586 merchants. The results and framework are already adopted and absorbed into the design for a cash-out group detection system in IoT by the Chinese payment processor.
format	article
author	Hao Zhou Ming Zhang Lei Pang Jian-Hua Li
author_facet	Hao Zhou Ming Zhang Lei Pang Jian-Hua Li
author_sort	Hao Zhou
title	Abnormal Detection of Cash-Out Groups in IoT Based Payment
title_short	Abnormal Detection of Cash-Out Groups in IoT Based Payment
title_full	Abnormal Detection of Cash-Out Groups in IoT Based Payment
title_fullStr	Abnormal Detection of Cash-Out Groups in IoT Based Payment
title_full_unstemmed	Abnormal Detection of Cash-Out Groups in IoT Based Payment
title_sort	abnormal detection of cash-out groups in iot based payment
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/a699ca26d2864046901fb29b2e5fda32
work_keys_str_mv	AT haozhou abnormaldetectionofcashoutgroupsiniotbasedpayment AT mingzhang abnormaldetectionofcashoutgroupsiniotbasedpayment AT leipang abnormaldetectionofcashoutgroupsiniotbasedpayment AT jianhuali abnormaldetectionofcashoutgroupsiniotbasedpayment
_version_	1718410545128800256

Abnormal Detection of Cash-Out Groups in IoT Based Payment

Ejemplares similares