Example systems and methods for dynamic identity decisioning include: receiving a request, from a third-party server, to confirm an identity of a user attempting a transaction through a third-party website displayed in a first application window on a user device of the user; causing the user device to display a second application window for presenting an identity decisioning application and at least partially overlapping the first window; assessing a risk level associated with the transaction based on identity verification data retrieved from the user device; and if the risk level exceeds a predetermined threshold, selecting at least one identity authentication exam for presentation to the user via the second window, determining an outcome of the at least one identity authentication exam based on a user response thereto, and determining an identity decisioning result based on the outcome; and presenting the result to the user via the second application window.

Examples described herein relate to apparatuses and methods of detecting fraudulent activity at an automated teller machine (ATM) using a machine learning model. A method includes receiving ATM activity data indicative of one or more withdrawal transactions at one or more ATMs using a transaction card, receiving transaction data and ATM data, ingesting the transaction data and the ATM data, analyzing the ingested transaction data and the ingested ATM data using a machine learning model, determining that the ingested transaction data and the ingested ATM data indicate fraudulent activity using the machine learning model, and performing one or more remedial actions based on the determination of fraudulent activity using the machine learning model.

Systems, methods, and computer program products for detecting merchant data shifts may identify a shift in transaction volume of a merchant system across Merchant Category Codes (MCCs) using a combination of time series analysis and machine learning.

The disclosure describes systems and techniques for assessing risk of an open Wi-Fi network, at a consumer's request, before the consumer performs a transaction. The system receives a Wi-Fi network risk assessment request associated with a Wi-Fi network connection of a mobile device. Upon receiving the request, the system retrieves connection-related data from the mobile device. The connection-related data is associated with the Wi-Fi network connection. The system performs a Wi-Fi risk assessment of the Wi-Fi network connection. The system transmits a result of the risk assessment to the mobile device for presentation on the mobile device. The system also transmits the result of the risk assessment to an issuer server. The issuer server is associated with a payment account of the consumer. Moreover, the system transmits a step-up authentication alert to the issuer server.

A system supports symmetric release of cryptologically-locked asset transactions. A leading exchange party and a reciprocal exchange party establish, at least in part, a peer challenge in a pre-exchange proposal. The reciprocal party uses the peer challenge to lock a cryptologically-locked asset transaction. The solution to the peer challenge corresponds to an exchange key controlled by the leading exchange party. After establishment of the cryptologically-locked asset transaction, the leading party may request that exchange logic initiate release of the cryptologically-locked asset transaction. In response to the request, the exchange logic may execute a symmetric release of the exchange key and/or signature to the reciprocal exchange party and cryptologically-locked asset transaction (such that the asset is transferred to the leading exchange party).

A system for identifying genuine user-merchant association. The system includes one or more processors and/or transceivers individually or collectively programmed to check the validity or expiration of a certificate from a device from which a request originates to create a certificate score, analyze previous communication from the device from which the request originates across a plurality of entities and regions to create a previous communication score, and conduct a messaging protocol check to create a protocol score. The one or more processors and/or transceivers are also programmed to output a weighted final score comprising a determination of whether to accept or deny the request based at least in part on one or more of the certificate scores, the previous communication score, or the protocol score. The one or more processors and/or transceivers are also programmed to save the weighted final score.

A system for processing a transaction at a point of engagement comprising receiving an input interaction from a user, communicating with a plurality of identity providers to validate an identity of the user, communicating with a plurality of payment providers to collect available payment or funding options, mapping the input interaction to an output interaction, and performing a transaction that reflects the mapping of the input interaction to the output interaction.

The system may be configured to perform operations including receiving a transaction history for a consumer having transaction information associated with a plurality of transactions; detecting within the transaction information for each transaction a characteristic, resulting in a plurality of characteristics; calculating a respective value associated with each characteristic, wherein the respective value is at least one of a number or percentage of transactions having the characteristic; assigning a respective weight to each characteristic, producing an assigned respective weight for each characteristic; applying the assigned respective weight to the respective value associated with each characteristic to produce a respective weighted value for each characteristic; combining the respective weighted values of the plurality of characteristics; and/or producing a compliance score in response to the combining the respective weight values.

The described technology relates to a deep learning based method and system for detecting abnormal cryptocurrency transaction between computing devices in a blockchain network. In once aspect, the method includes generating, at a server, a first data set, a second data set, and a third data set from the transactions of a user wallet address with at least one other user wallet address. The method may also include running a pre-learned deep learning module to extract a first feature vector, a second feature vector, and a third feature vector from the first data set, the second data set, and the third data set. The method may further include converting the first feature vector, the second feature vector, and the third feature vector into an intermediate value and comparing the intermediate value to a predetermined reference value to determine if a fraudulent transaction associated with the user wallet address has occurred.

An approach for locating suspect patterns of transactions in a financial network may be provided. The approach may include generating a transaction graph for a financial network by processing transaction data defining transfers between accounts in that network. The approach may include modifying the transaction graph to include synthetic suspect transaction patterns at multiple locations in the graph and extracting subgraphs from the transaction graph. The approach may include training a graph neural network model to classify subgraphs containing a synthetic suspect transaction pattern as suspect. The approach may also include locating suspect transaction patterns in a new financial network by generating a new transaction graph for that network and classifying a subgraph of the new financial network as suspect.