公开(公告)号：US12141807B2

公开(公告)日：2024-11-12

申请号：US17763255

申请日：2019-10-31

Applicant: VISA INTERNATIONAL SERVICE ASSOCIATION

Inventor： Liang Wang ,  Dhruv Gelda ,  Robert Christensen ,  Wei Zhang ,  Hao Yang ,  Yan Zheng

IPC: G06Q20/40 ,  G06Q30/018

Abstract: The system and method may assess the merchant risk level on a more continuous scale rather than a binary categorization. It may produce a continuous risk score proportional to the likelihood of a merchant being risky, effectively addressing the issue of shades of gray encountered by the traditional blacklisting approach. The continuous risk score feature provides greater flexibility as it allows the payment network to make dynamic pricing decisions (known as interchange optimization) based on the merchant risk level. Using collective intelligence from transactions across the payment network, the system and method may be able to assess the merchant risk level with high accuracy. The system and method may be particularly beneficial to small merchants with low transaction volume as even a few fraudulent transactions can easily put them in the high-risk merchant category. Further, the system and method may help payment processing networks make better decision on cross-border transactions.

公开(公告)号：US20220366421A1

公开(公告)日：2022-11-17

申请号：US17763255

申请日：2019-10-31

Applicant: VISA INTERNATIONAL SERVICE ASSOCIATION

Inventor： Liang Wang ,  Dhruv Gelda ,  Robert Christensen ,  Wei Zhang ,  Hao Yang ,  Yan Zheng

IPC: G06Q20/40 ,  G06Q30/00

Abstract: The system and method may assess the merchant risk level on a more continuous scale rather than a binary categorization. It may produce a continuous risk score proportional to the likelihood of a merchant being risky, effectively addressing the issue of shades of gray encountered by the traditional blacklisting approach. The continuous risk score feature provides greater flexibility as it allows the payment network to make dynamic pricing decisions (known as interchange optimization) based on the merchant risk level. Using collective intelligence from transactions across the payment network, the system and method may be able to assess the merchant risk level with high accuracy. The system and method may be particularly beneficial to small merchants with low transaction volume as even a few fraudulent transactions can easily put them in the high-risk merchant category. Further, the system and method may help payment processing networks make better decision on cross-border transactions.

公开(公告)号：US20240330712A1

公开(公告)日：2024-10-03

申请号：US18740960

申请日：2024-06-12

Applicant: Visa International Service Association

Inventor： Liang Wang ,  Xiaobo Dong ,  Robert Christensen ,  Liang Gou ,  Wei Zhang ,  Hao Yang

IPC: G06N5/02 ,  G06N3/045 ,  G06N3/08 ,  G06Q30/018

CPC classification number: G06N5/02 ,  G06N3/045 ,  G06N3/08 ,  G06Q30/0185

Abstract: A system, method, and computer program product for incorporating knowledge from more complex models in simpler models. A method may include obtaining first training data associated with a first set of features and second training data associated with a second set of features different than the first set of features; training a first model based on the first training data and the second training data; and training a second model, using a loss function that depends on an output of an intermediate layer of the first model and an output of the second model, based on the second training data.

公开(公告)号：US12039458B2

公开(公告)日：2024-07-16

申请号：US16244240

申请日：2019-01-10

Applicant: Visa International Service Association

Inventor： Liang Wang ,  Xiaobo Dong ,  Robert Christensen ,  Liang Gou ,  Wei Zhang ,  Hao Yang

IPC: G06N3/08 ,  G06N3/045 ,  G06N5/02 ,  G06Q30/018

CPC classification number: G06N5/02 ,  G06N3/045 ,  G06N3/08 ,  G06Q30/0185

Abstract: A system, method, and computer program product for incorporating knowledge from more complex models in simpler models. A method may include obtaining first training data associated with a first set of features and second training data associated with a second set of features different than the first set of features; training a first model based on the first training data and the second training data; and training a second model, using a loss function that depends on an output of an intermediate layer of the first model and an output of the second model, based on the second training data.

公开(公告)号：US20200226476A1

公开(公告)日：2020-07-16

申请号：US16244240

申请日：2019-01-10

Applicant: Visa International Service Association

Inventor： Liang Wang ,  Xiaobo Dong ,  Robert Christensen ,  Liang Gou ,  Wei Zhang ,  Hao Yang

IPC: G06N5/02 ,  G06Q30/00

Abstract: A system, method, and computer program product for incorporating knowledge from more complex models in simpler models. A method may include obtaining first training data associated with a first set of features and second training data associated with a second set of features different than the first set of features; training a first model based on the first training data and the second training data; and training a second model, using a loss function that depends on an output of an intermediate layer of the first model and an output of the second model, based on the second training data.