Mastercard International

There is provided a merchant computing device for processing a transaction between a cardholder computing device and the merchant computing device, the merchant computing device comprising: a processor; and a memory storing instructions that, when executed by the processor, cause the processor to: generate authorisation data comprising a merchant verification code; send the authorisation data to the cardholder computing device for generating an authorisation request for approval by an issuer associated with the cardholder; if the authorisation request is approved by the issuer, receive an authorisation approval comprising the authorisation data from the cardholder computing device, wherein the authorisation approval has been generated by the issuer; verify whether the authorisation data provided within the authorisation approval matches the generated authorisation data; in dependence on the match being obtained, complete the transaction. There is also provided a corresponding cardholder computing device for processing a transaction between the cardholder computing device and the merchant computing device.

A method of authorising a transaction using a payment network is described. A token for the transaction, associated with a payment account, is determined. At a node in the payment network, a succession of time steps are established. The transaction is performed, using the token. For this, a dynamic transaction credential is obtained from the node in the payment network. This dynamic transaction credential is determined by the time step in which the dynamic transaction credential is generated. The transaction is provided to the payment network for authorisation. The dynamic transaction credential is validated in the payment network by determining the time step in which the dynamic transaction credential was generated. Methods of validating such a credential are also described, in particular such that a plurality of candidate values for the credential can be evaluated in a single process. Computer systems adapted to perform such methods are also described.

Techniques are disclosed for processing service requests in a payment network. A receiving server that cannot process a service request identifies another server within the payment network that can process the service request based on some digits extracted from sensitive numerical data contained within the service request. The receiving server responds to the service request with a redirect message including an address of the server that can process the service request. The redirect message also includes a numerical range corresponding to service requests that the server can process. A merchant device stores the numerical range and address information in a lookup table such that future service requests can be routed according to the lookup table. Optionally, the redirect message is a HTTP 302 response, the sensitive numerical data is a PAN, the group of digits is a BIN or IIN and the numerical range is an account range.

The present invention provides a computer implemented method for detecting fraud using a fraud detection model. The method comprises identifying (501) a transaction from a plurality of transactions occurring over a payment network and receiving (503) details of a source account of the identified transaction. The method further comprises determining (505): a rate at which further transactions occur from the source account, total amount in refunds received by the source account within the predetermined time period, and a total amount in funds sent from the source account, all within a predetermined time period, calculating (509) a feature based on the determined factors and inputting (511), into a fraud detection model, the calculated feature to detect if the source account is associated with fraudulent activity.

A computer-implemented method is disclosed for effecting an electronic payment. The method involves a user device establishing a first communication channel with a merchant system comprising a plurality of merchant devices using a first wireless communication protocol. The user device and merchant system exchange ultra-wideband (UWB) capability data via the first communication channel to establish an UWB ranging session including the user device and the plurality of merchant devices. A proximate merchant device that is closest to the user device is determined using the UWB ranging session. An NFC channel or optical channel is established between the proximate merchant device and the user device, and a correlation identifier that uniquely identifies the user device is transmitted from the user device to the proximate merchant device via the NFC channel or optical channel. The user device transmits payment data either via the NFC channel/optical channel or via the first communication channel.

The present invention provides a computer implemented method for determining if a merchant account is associated with fraudulent activity. The method comprises receiving (601) data relating to a fraudulent merchant account, determining (603) a total amount in funds returned to one or more customer accounts due to one or more disputed transactions between the merchant account and the one or more customer accounts within a predetermined period of time, and a total amount in funds received by the merchant account within the predetermined period of time, and determining (605) a ratio of these two values. The method further comprises labelling (609) the ratio value as indicating that the merchant account is associated with fraudulent activity and inputting (611), into a machine learning model, the labelled ratio value to train the machine learning model to predict fraudulent activity based on the ratio.

The present invention relates to a computer implemented method to detect threats in a payment network using a threat detection algorithm by limiting the growth of a data tree, for use with a threat detection algorithm. The method comprises, receiving (1003) transaction data relating to a first transaction, and retrieving (1001) a data tree comprising a first node connected to a second node representing a second transaction, where the source account of the first transaction is the same as the destination account of the second transaction. The method further comprises determining (1005) a difference in time between the time of the second transaction and the time of the first transaction and determining (1007) a total number of accounts that have made a transaction with the source account of the first transaction. If the difference between the time of the second transaction and the time of the first transaction is less than a first predetermined length of time, and the total number of accounts to have made a transaction with the source account of the first transaction is less than a predetermined number of accounts, the data tree is updated (1009) to comprise a third node connected to the second node, the third node representing the destination account of the first transaction, and is inputted (1011) into a threat detection algorithm, to thereby detect threats in a payment network using the threat detection algorithm.

The present disclosure relates to methods for preventing tokenized payment fraud. The methods include receiving a second request from a user device to provision token credentials related to a funding account and provisioning second token credentials to the user device in response to the second request. The second token credentials include an account identifier, expiry data, and a token PAN sequence number that are identical to the account identifier, expiry data and token PAN sequence number of first token credentials. In one fraud prevention solution, a token cryptographic sequence number is stored in discretionary data provisioned to the user device. In a second fraud prevention solution, a token cryptographic sequence number is stored away from the user device.

The present invention relates to a computer implemented method 500 for preventing a security threat in a computing network. The method comprises receiving 501 a data packet originating associated with an autonomous system number (ASN) and determining 503 if the ASN is in a list of stored ASNs, wherein the list of stored ASNs comprises ASNs each associated with a previous data packet received by the computer network. If the received ASN is not in the list, the method further comprises blocking (505) the received data packet from being sent to the destination IP address in the computer network.

A computer-implemented method is provided for providing proof for a digital transaction between a consumer and a merchant. The proof comprises sensitive data of one or both the consumer and the merchant. The method comprises determining a transaction type, and also determining security requirements for the determined transaction type. The proof is then prepared by one of a plurality of methods to meet the security requirements for the determined transaction type. A payment device adapted to perform such a method is also described.