Abstract: A method for processing a chargeback request associated with at least one online transaction associated with a user includes: receiving a chargeback message associated with the at least one online transaction; based at least partially on the unfamiliar merchant name in the chargeback message, determining at least one potential familiar merchant name associated with the at least one unfamiliar merchant name; scanning a browser history of the user including browser data; determining whether the user visited a website associated with the at least one potential familiar merchant name; and generating and communicating a recommendation message including the at least one potential familiar merchant name. A system for processing a chargeback request associated with at least one online transaction associated with a user is also disclosed.

Abstract: A verification application executing at a user's mobile phone directs the user to take a photo of an identification document (e.g., driver's license or other form of government issued identification) or of their face. After the verification application sends the image to a backend service, the service may then dispatch a drone to the user's location and take a photograph of the user. The service may then validate the previously-imaged document or photo of the user's face against the photograph of the user and the geolocation sent with the first image. The service may then verify the new account and provision a token to the verification application to complete a secured account generation.

Abstract: A method includes a deployment computer receiving a client request message comprising a plurality of established parameters and established values for the established parameters, and inquiry parameters and inquiry values for the inquiry parameters from a client computer. For each model of a plurality of models stored in a database, the deployment computer can determine if a model in the plurality of models is a suitable model based on a likelihood value. The deployment computer can then generate one or more client response messages comprising one or more assets created by one or more suitable models. The deployment computer can then transmit the one or more client response messages comprising the one or more assets to the client computer.

Abstract: Methods for generating fraud detection rules based on transaction data may include receiving historical transaction data, associating tags with each transaction, generating decision trees having root nodes and child nodes operably connected to the respective root nodes, determining at least one primary rule and at least one set of secondary rules associated with the at least one primary rule based on relationships between features of the transactions, assigning primary rules and sets of secondary rules to the at least one decision tree to populate the tree, extracting a plurality of rule sets including at least one primary rule and one or more secondary rules, determining an ordering of the plurality of rule sets; and determining a subset of rule sets from the ordered plurality of rule sets against which subsequently received transactions are compared against to determine if the subsequent transactions are fraudulent.

Abstract: A portal to provide user interfaces to users to access and/or purchase account features in connection with websites of issuers. The user interfaces have white label configurability that allows the issuers to customize the labeling of the user interfaces such that the user interfaces can be perceived as part of the websites of the issuers of the consumer accounts of the respective users. The user interfaces are configured to present, in a user friendly way, the account features currently in the consumer accounts, as well as optional account features that can be purchased at additional costs.

Abstract: The ELECTRONIC WALLET CHECKOUT PLATFORM APPARATUSES, METHODS AND SYSTEMS (“EWCP”) transform customer purchase requests triggering electronic wallet applications via EWCP components into electronic purchase confirmation and receipts. In one implementation, the EWCP receives a merchant payment request, and determines a payment protocol handler associated with the merchant payment request. The EWCP instantiates a wallet application via the payment protocol handler. The EWCP obtains a payment method selection via the wallet application, wherein the selected payment method is one of a credit card, a debit card, a gift card selected from an electronic wallet, and sends a transaction execution request for a transaction associated with the merchant payment request. Also, the EWCP receives a purchase response to the transaction execution request, and outputs purchase response information derived from the received purchase response.

Abstract: Described herein is a system in which an electronic record is stored within a distributed environment. In this system, a validation node may receive a transaction record from an acceptance node. The validation node may verify that the acceptance node is authorized 5 to participate in a blockchain network, identify a user associated with the transaction record, and append the transaction record to an electronic record. The transaction record may be associated with a digital signature formed by hashing multiple data elements, and then encrypting the hashed data elements using a private encryption key.

Abstract: Embodiments are directed to issuing tokens for identifiers associated with a resource provider account specific to the resource provider issuing the account. A resource provider processor system interfaces with a resource provider computer to validate account eligibility upon receiving a token request message. If the account is eligible for token generation, the resource provider processor system generates a universal identifier corresponding to the identifier associated with the resource provider account and returns the universal identifier to the token requestor. The token requestor may send a token request message to a token issuer for obtaining a token using the universal identifier. Accordingly, the universal account identifier can be used to provision a token into a digital wallet. Transactions using the token may be processed with the resource provider processor system acting as an account issuer.

Abstract: Embodiments of the invention are directed to methods, systems, and devices for replacing a token on a user device, such as a transaction card. The transaction card includes tokens representing an actual account identifier which is not visible on the transaction card. The transaction card may store a first token on a and include a digital display that displays a second token. When the first token or the second token is compromised, the compromised token is replaced without replacing the transaction card. When the second token is compromised, the compromised token is replaced with a new replacement second token using an electronic device. The replacement second token replaces the old second token on the digital display. After the second token is compromised and before the replacement second token is provisioned on the transaction card, the transaction card may still be used for transactions using other tokens provisioned on the card.

Abstract: A method includes broadcasting, by a node computer, a propose message comprising a new block for a blockchain to a plurality of node computers in a network shard. The node computer can receive at least one vote message from the plurality of node computers, the at least one vote message indicating verification of the new block. The node computer can, after a predetermined amount of time, receive a plurality of pre-commit messages comprising at least the new block and a block certificate created based on the at least one vote message. If the number of received pre-commit messages of the plurality of pre-commit messages is greater than a quorum value associated with the network shard, the node computer can commit the new block to the blockchain.

Abstract: A method for identifying subpopulations may include receiving interaction data associated with interactions from a population of individuals. The interaction data may include a plurality of features. A first subpopulation may be identified based on at least one feature of interaction data of each individual. A second subpopulation may include all individuals other than the first subpopulation. The first subpopulation may be clustered into a first plurality of clusters based on the features. A first subset of features may be determined based on the first clusters. The first subpopulation may be clustered into a second plurality of clusters based on the first subset of features. A range for each feature of a second subset of features may be determined based on the second clusters. A subset of the second subpopulation may be determined based on interaction data for each individual and the range for each feature of the second subset of features.

Abstract: A payment device for conducting a transaction is provided. The payment device includes a device substrate, a payment device identifier visibly located on the device substrate, and a data storage region contained on or within the payment device. The payment device identifier does not include information identifying an issuer for the payment device. The data storage region comprises a first data storage sub region containing data corresponding to the payment device identifier, and a second data storage sub region electronically isolated from the first data storage sub region and containing data identifying the issuer of the payment device.

Abstract: Techniques managing access rules are provided. Access rules and their associated profiles are determined for evaluation. A triggering rate or a triggering percentage can be used to indicate efficacy of the rule. Recommendations can be provided based on a triggering percentage difference of the rule during a predetermined period of time. The recommendations can be provided in an interactive user interface.

Abstract: A method to display an illustration to conduct an expedited electronic transaction is provided. Consumer identification information identifying a consumer is received. The consumer identification information is stored in association with a web browser of a consumer's device. A customized illustration is displayed based on the received consumer identification information on the consumer's device. A request is received for the expedited electronic transaction by swiping the customized illustration across a portion of the display of the consumer's device. Transaction data sufficient to complete the electronic transaction is sent to the merchant based on the swipe of the customized illustration across display of the consumer's device.

Abstract: A system for storing and managing secure information is disclosed that includes a secure identity and profiling system, which serves as a middleman between a user and an entity requesting personally identifiable information (PII) from the user. The system collects the PII from the user and stores it securely, such as in an alternate blockchain in an encrypted form. The location of the that PII within the alternate blockchain may be indexed using smart contracts in a main blockchain that can only be read with an access token generated and supplied by the user's mobile device. When an entity requests PII from the user that has already been collected and securely stored, the user can provide permission to release that PII by providing the access token. The system will use the access token to locate where the PII is stored and release the PII to the requesting entity.

Abstract: A system and method for using a deep learning model to learn program semantics is disclosed. The method includes receiving a plurality of execution traces of a program, each execution trace comprising a plurality of variable values. The plurality of variable values are encoded by a first recurrent neural network to generate a plurality of program states for each execution trace. A bi-directional recurrent neural network can then determine a reduced set of program states for each execution trace from the plurality of program states. The reduced set of program states are then encoded by a second recurrent neural network to generate a plurality of executions for the program. The method then includes pooling the plurality of executions to generate a program embedding and predicting semantics of the program using the program embedding.

Abstract: An automation computer can receive a set of instructions pertaining to a transaction. The automation computer can generate a request to generate and activate a virtual account, where the virtual account is associated with a transaction value and a transaction amount. The virtual account can be managed by an authorization computer that can load a transaction value onto the virtual account in an amount equal to the transaction amount. The authorization computer managing both issuer and acquirer functionality in a transaction settlement can settle the transaction rapidly using the loaded virtual account by depositing the transaction value associated with the virtual account directly into an account of a resource provider.

Abstract: A method includes receiving a first data set comprising embeddings of first and second types, generating a fixed adjacency matrix from the first dataset, and applying a first stochastic binary mask to the fixed adjacency matrix to obtain a first subgraph of the fixed adjacency matrix. The method also includes processing the first subgraph through a first layer of a graph convolutional network (GCN) to obtain a first embedding matrix, and applying a second stochastic binary mask to the fixed adjacency matrix to obtain a second subgraph of the fixed adjacency matrix. The method includes processing the first embedding matrix and the second subgraph through a second layer of the GCN to obtain a second embedding matrix, and then determining a plurality of gradients of a loss function, and modifying the first stochastic binary mask and the second stochastic binary mask using at least one of the plurality of gradients.

Abstract: Secure protocols for external-facing authentication are provided for both user templates stored on their devices and the biometric measurement captured by external sensors of an access device. The protocols provide different levels of security, ranging from passive security with some leakage to active security with no leakage. A packing technique is also provided. Zero-knowledge techniques are used during enrollment to validate a norm of user templates and knowledge of the plaintext biometric template. Once enrolled, the verifier can sign the encrypted template for use in a later matching phase with an access device.

Abstract: An issuing authority (IA) may validate the identity of a user and issue a digital license to the user. IA may generate IA public-private key pair, and provide IA public key to the certification authority (CA). IA may sign the digital license with IA private key, and provision the signed digital license on the user device. IA may request CA to certify the digital license. CA may use IA public key to validate the digital license, and sign IA public key with CA private key, thereby generating a digital certificate associated with the issuing authority that is linked to the digital license. A relying party may use CA public key to validate the digital license. The relying party can retrieve the information from the digital license and trust that the retrieved information is legitimate.