Abstract: One embodiment of the invention is directed to a method comprising, receiving an authentication request message for a transaction. The method further comprises determining that detailed device information is required to authenticate the transaction and generating a message including an identifier and a request for the detailed device information. The method further comprises retrieving the detailed device information from a remote server computer using the identifier and modifying the authentication request message to include the detailed device information. The method further comprises sending the modified authentication request message to an access control server computer. The method further comprises receiving an authentication response message from the access control server computer including a verification value for the transaction, where the verification value is generated based on a result of a risk analysis performed using the detailed device information.

Abstract: Embodiments are directed to a method for accelerating machine learning using a plurality of graphics processing units (GPUs), involving receiving data for a graph to generate a plurality of random samples, and distributing the random samples across a plurality of GPUs. The method may comprise determining a plurality of communities from the random samples using unsupervised learning performed by each GPU. A plurality of sample groups may be generated from the communities and may be distributed across the GPUs, wherein each GPU merges communities in each sample group by converging to an optimal degree of similarity. In addition, the method may also comprise generating from the merged communities a plurality of subgraphs, dividing each sub-graph into a plurality of overlapping clusters, distributing the plurality of overlapping clusters across the plurality of GPUs, and scoring each cluster in the plurality of overlapping clusters to train an AI model.

Abstract: A method includes a) receiving, by a computer, network data comprising a plurality of transactions conducted by a plurality of actual users and a plurality of actual resource providers. The computer can b) generate a plurality of simulated users. Each simulated user based upon a set of the plurality of actual users. The computer can then c) generate a plurality of simulated resource providers. Each simulated resource provider based upon at least one actual resource provider. The computer can d) execute a simulation using the plurality of simulated users and the plurality of simulated resource providers, and in response to step d) can e) determine a plurality of simulated transactions conducted by the plurality of simulated users and the plurality of simulated resource providers.

Abstract: Systems and methods are provided for transcompiling non-distributed source code for a non-distributed software program into a distributed software package for implementation on a distributed computing system. A transcompiler can identify loops within non-distributed source code written in a data-driven language. The transcompiler can generate MapReduce jobs using mapper keys based on grouping indicators associated with each of the loops. The MapReduce jobs can be linked together based on input-output connections of the loops in the non-distributed source code. Then, the transcompiler can generate a distributed software package including the generated MapReduce jobs to implement the same functionality as the non-distributed source code on the distributed computing system, thereby improving the speed of execution over very large datasets. The distributed software package can be optimized using machine learning searching algorithms.

Abstract: A computer-implemented method of using past transaction declines to predict future fraudulent behavior. A transaction has been declined for an account is determined, and a risk score is determined. The risk score is compared to a risk threshold. The transaction is compared to one or more transactions in a transaction profile for a past fraudster in response to the risk score being determined to be over the risk threshold. A best fit of the transaction profiles of the past fraudster is determined and a measure of success for the best fit of the transaction profiles of the past fraudster is also determined. If the measure of success is over a threshold, the method updates profiles of past fraudsters based on the transaction to include the transaction that has been declined. The method predicts future fraudulent transactions and attempts to stop future fraudulent transactions based on the predicted future fraudulent transactions.

Abstract: One embodiment of the invention is directed to a method comprising, receiving an authentication request message for a transaction. The method further comprises determining that detailed device information is required to authenticate the transaction and generating a message including an identifier and a request for the detailed device information. The method further comprises retrieving the detailed device information from a remote server computer using the identifier and modifying the authentication request message to include the detailed device information. The method further comprises sending the modified authentication request message to an access control server computer. The method further comprises receiving an authentication response message from the access control server computer including a verification value for the transaction, where the verification value is generated based on a result of a risk analysis performed using the detailed device information.

Abstract: A method includes a processing computer querying a data store for plurality of network data since a last epoch of data. The processing computer can generate matrices based on the plurality of network data and then perform tensor factorization on the matrices, to obtain latent values in the network data. The processing computer can then determine that the latent values satisfy a predetermined criterion. The processing computer can input the latent values into a model associated with the signal, wherein the model generates output data. The processing computer can then generate an alert comprising the output data and then transmit the alert to a remote server computer.

Abstract: A method includes a processing computer receiving a processing request message comprising user data from a remote server computer. The processing computer can then determine latent values associated with the processing request message based on the user data and a multiplex graph. The processing computer can then normalize the latent values based on a community group in the multiplex graph. The community group can include at least a part of the user data. The processing computer can transmit a processing response message comprising at least one normalized latent value to the remote server computer.

Abstract: Systems and methods are provided for transcompiling non-distributed source code for a nondistributed software program into a distributed software package for implementation on a distributed computing system. A transcompiler can identify loops within non-distributed source code written in a data-driven language. The transcompiler can generate MapReduce jobs using mapper keys based on grouping indicators associated with each of the loops. The MapReduce jobs can be linked together based on input-output connections of the loops in the non-distributed source code. Then, the transcompiler can generate a distributed software package including the generated MapReduce jobs to implement the same functionality as the non-distributed source code on the distributed computing system, thereby improving the speed of execution over very large datasets. The distributed software package can be optimized using machine learning searching algorithms.

Abstract: Embodiments are directed to a method for determining an interview script in a claims submission. The method may comprising receiving data relating to a claim being submitted, which may include claims submission data input by a user, information relating to the user, and one or more features. Data associated with the one or more features may be determined from an artificial intelligence model. A first score based on the data associated with the one or more features and data associated with the information relating to the user may be determined and used to determine an interview script. In one embodiment, questions in the interview script may continue to be provided to the interviewer computer if a continually updated score remains above a predetermined threshold. In another embodiment, the user may be routed to a live interview with a human representative if a continually updated score drops below a predetermined threshold.

Abstract: Methods, systems, and devices are disclosed for using a payment processing network as an authorization engine to access secure physical areas, such as college dormitories, office buildings. A keycard with a cryptogram generator is presented by a user to an access device, and the access device or associated computer sends an access request message formatted like a payment authentication request message to an aggregator/acquirer and payment processing network. The payment processing network validates the cryptogram and returns an access response message, again formatted like a payment authorization response message, indicating that the keycard is authentic. The gate, door, turnstile, or other barrier is then temporarily unlocked to let the user through.

Abstract: Embodiments of the invention are directed to methods and devices for predicting interactions. One embodiment is directed to a method comprising receiving, by one or more computers, interaction data for a plurality of known interactions between resource providers and users, and creating a topological graph based on the plurality of known interactions. The method may further comprise determining, by the one or more computers, a plurality of communities to form a predictive model, and receiving a request for a prediction. In addition, the method may comprise applying the request to the predictive model, by the one or more computers, by identifying a community in the plurality of communities corresponding to the request, determining a node within the identified community, and providing information regarding the node as the requested prediction.

Abstract: Embodiments of the present invention are directed to methods and systems for utilizing the history of previous authentications and authorizations related to third party computers, as factors in determining whether a current request for accessing a resource should be authorized. A processor server computer, in determining whether to authorize access to the resource, may generate and send a query message to one or more of the third party computers to obtain authorization activity that the third party computers may have regarding a user and/or a device associated with the request. The processor server computer may use the authorization activity from the third party computers in determining whether the request is an authentic request and that the request should be authorized.

Abstract: Embodiments of the invention are directed to methods and devices for predicting interactions. One embodiment is directed to a method comprising receiving, by one or more computers, interaction data for a plurality of known interactions between resource providers and users, and creating a topological graph based on the plurality of known interactions. The method may further comprise determining, by the one or more computers, a plurality of communities to form a predictive model, and receiving a request for a prediction. In addition, the method may comprise applying the request to the predictive model, by the one or more computers, by identifying a community in the plurality of communities corresponding to the request, determining a node within the identified community, and providing information regarding the node as the requested prediction.

Abstract: Systems and methods are provided for transcompiling non-distributed source code for a nondistributed software program into a distributed software package for implementation on a distributed computing system. A transcompiler can identify loops within non-distributed source code written in a data-driven language. The transcompiler can generate MapReduce jobs using mapper keys based on grouping indicators associated with each of the loops. The MapReduce jobs can be linked together based on input-output connections of the loops in the non-distributed source code. Then, the transcompiler can generate a distributed software package including the generated MapReduce jobs to implement the same functionality as the non-distributed source code on the distributed computing system, thereby improving the speed of execution over very large datasets. The distributed software package can be optimized using machine learning searching algorithms.

Abstract: Embodiments of the present invention relate to linking a prepaid account with a payment account used to fund the prepaid account. In some embodiments, during payment for a prepaid device, an authorization request message may include a prepaid account identifier associated with the prepaid account. In some embodiments, an activation request message may include a payment account identifier associated with the payment account. A server at the payment processing network may store an association between the prepaid account identifier and the payment account identifier in an account link database. In some embodiments of the invention, if the payment account is canceled, the payment processing network may use the account link database to cancel any associated prepaid accounts, and may transfer funds associated with corresponding prepaid accounts to an issuer associated with the payment account.

Abstract: Client devices can send access request messages to resource management computers to request access to a resource. A data security hub can provide centralized routing between different client devices, resource management computers, and authentication data processing servers. The data security hub can reduce the risk of sensitive authentication information from leaking (e.g., due to a breach) by limiting the amount or types of authentication information distributed to the data processing servers. The data security hub can limited the authentication information being distributed based on its sensitivity, the trust level of the client device, and the security level of the requested resource. The data security hub can also evaluate the client devices and data processing servers to identify security breaches and can cancel or reroute access requests accordingly Thus, the data security hub can maintain resource security while better preserving the privacy of the client device's authentication information.

Abstract: A method including collecting, by a communication device comprising a machine learning model obtained at least in part from a server computer, metadata associated with an application. The communication device can then embed the metadata to form vectorized data. The communication device can input the vectorized data into the machine learning model to obtain a security value. The communication device can determine whether to run or install the application based upon the security value.

Abstract: A system for providing real-time risk mitigation for an authorization system. The system receives authorization requests from multiple merchants (or their respective acquirers) and processes such requests. Each processed request is then forwarded to its corresponding issuer for further authorization. Each processed request includes an authorization message. The authorization message can include a risk score, a number of reason codes, and a number of condition codes. The use of the risk score, reason codes and condition codes allows issuers to make better informed decisions with respect to providing authorizations.

Abstract: Embodiments of the invention are directed to systems and methods of user authentication for data services. The data services may include accessing a tax return at the IRS, accessing or completing a student loan application, accessing a credit report, etc. User authentication data is collected by a data provider and provided to a server computer, and user device data is collected by the server computer after the user device accesses a resource identifier (e.g., URL) associated with the server computer. The user authentication data and/or user device data is analyzed and a risk score is generated.