Abstract: An ultra-wideband (UWB)-enabled payment acceptance system can include a UWB anchor and a terminal device. The UWB anchor identifies UWB-enabled devices within a vicinity; and in response to receiving an indication of an intent to perform a payment transaction from a particular UWB-enabled device, the UWB anchor establishes a secure communication channel with the particular UWB-enabled device. The terminal device, via the UWB anchor, communicates transaction related information over the secure communication channel to the particular UWB-enabled device and receives a transaction payload from the particular UWB-enabled device over the secure communication channel. A UWB-enabled device includes a processor, storage, a battery, and a UWB chip. Instructions can be stored in the storage of the UWB-enabled device that when executed by the processor direct the UWB-enabled device to perform various processes supporting frictionless transactions, such as with respect to the UWB-enabled payment acceptance system.

Abstract: Methods and systems for providing a refund amount to a customer account for a payment transaction that occurred using a real-time payment network. In an embodiment, a supplemental payment services computer receives a refund request including a transaction reference and a token concerning a payment transaction between a merchant and a customer, determines that the payment transaction was effected in a real-time payment network, determines an issuer financial institution (FI) computer of an issuer FI maintaining a customer account represented by the token, transmits the refund request to the issuer FI computer, receives a favorable authorization response and transmits the authorization response to an acquirer FI computer associated with the merchant.

Abstract: A method for generating a block for a blockchain utilizing an all-or-nothing transform includes: storing, in a memory of a blockchain node in a blockchain network, a blockchain comprised of a plurality of blocks including at least a most recent block; receiving a plurality of blockchain transactions; applying an all-or-nothing transform (AONT) to the plurality of blockchain transactions to generate a plurality of pseudomessage blocks; generating a new block header including at least a timestamp and a hash value associated with the most recent block; generating a new block including at least the generated new block header and the plurality of pseudomessage blocks; and transmitting the generated new block to a plurality of additional blockchain nodes in the blockchain network.

Abstract: A method for verification of a data value via a Merkle root includes: storing, in a memory of a processing server, a Merkle root; receiving at least a data value, a nonce, and a plurality of hash path values; generating a combined value by combining the data value and the nonce; generating a first hash value via application of a hashing algorithm to the combined value; generating a subsequent hash value via application of the hashing algorithm to a combination of the first hash value and a first of the plurality of hash path values; repeating generation of the subsequent hash value using a combination of the next hash path value of the plurality of hash path values and the most recent subsequent hash value; and verifying the data value based on a comparison of the Merkle root and the last generated subsequent hash value.

Abstract: A method for generating payment credentials in a payment transaction includes storing, in a memory, at least a card master key associated with a transaction account. The method also includes generating, by a processing device, a first session key based on at least the stored card master key; generating, by the processing device, a second session key; generating, by the processing device, a first application cryptogram based on at least the first session key; generating, by the processing device, a second application cryptogram based on at least the second session key; and transmitting, by a transmitting device, at least the first application cryptogram and second application cryptogram for use in a payment transaction.

Abstract: A method for building an advanced storage key includes: storing, in a mobile device, at least (i) device information associated with the mobile device, (ii) program code associated with a first program including an instance identifier, and (iii) program code associated with a second program including a first key; generating a device fingerprint associated with the mobile device based on the device information via execution of the code associated with the first program; generating a random value via execution of the code associated with the first program; building a diversifier value based on the generated device fingerprint, the generated random value, and the instance identifier included in the code associated with the first program; and decrypting the built diversifier value using the first key stored in the code associated with the second program via execution of the code associated with the second program to obtain a storage key.

Abstract: A method for enabling the use of blockchain smart contracts as part of a traditional payment transaction includes: receiving, by a receiver of a processing server, a transaction message for a payment transaction, wherein the transaction message is formatted according to one or more standards and includes a plurality of data elements storing transaction data, the transaction data including at least a bank identification value; determining, by a processor of the processing server, a routing plan for the transaction message based on at least the bank identification value; and transmitting, by a transmitter of the processing server, the transaction message to (i) a first computing system using a first communication port of the processing server, and (ii) a second computing system using a second communication port of the processing server, based on the determined routing plan.

Abstract: The disclosure relates to methods and systems of joining data structures based on a composite similarity score (CSS). For example, a computer system may use a plurality of similarity models to generate respective similarity scores. Each similarity score may be a metric that indicates a confidence that a first data value of a first data record is similar to a second data value of a second data record. The computer system may generate the CSS based on the plurality of similarity sub-scores. The CSS may indicate a confidence that the records being compared are similar. Thus, the CSS may be used to detect similar data records across different data structures. The disclosure also relates to a string similarity model that detects similarity among strings without respect to an order of words in each string and in a way that tolerates errors or omissions in one or both strings.

Abstract: Systems, apparatuses and methods may provide for technology to store hardware details associated with a plurality of hardware components of a computing device. The technology further extracts a first hardware identifier from first authentication data received from the computing device, where the first hardware identifier is associated with a first hardware component of the computing device, and determines whether to validate the first hardware component based on a comparison of the first hardware identifier to a first hardware detail of the hardware details.

Abstract: Disclosed herein are systems and methods that identify and improve upon false positive scores. Some embodiments may include artificial neural network learning methods that utilize data input from users as well as enterprise machines. Information, such as transaction timing, prior transaction data, and demographics, may be taken as inputs to the neural network processing. The processing may be done on one or more neural network computers or nodes.

Abstract: A computer-implemented method for authenticating an individual to one or more IoT devices. The method may include: receiving active behavioral data from the personal electronic device; retrieving an active behavioral profile corresponding to the individual; comparing the active behavioral data with the active behavioral profile; and authenticating the individual based at least in part on the comparison.

Abstract: Provided herein is a computing system for electronically transmitting a token linked to personally identifying information (PII) of a user to a merchant. The computing system includes a processor in communication at a memory device, and the processor is programmed to: (i) receive PII, issued payment instrument data, and a user identifier associated with a user, (ii) store the PII, issued payment instrument data, and user identifier in the memory device, (iii) receive an identification request for a user associated with a transaction including payment instrument data, (iv) perform a lookup in the memory device to retrieve the PII of the user and the stored user identifier associated with the received payment instrument data, (v) receive a user input identifier from the user to authenticate the user, (vi) generate a token that links the PII of the user to the transaction, and (vii) transmit the token to the merchant.

Abstract: A transaction card comprises a piezoelectric chip configured to detect an impact applied to at least a portion of the transaction card, and generate an electrical pulse signal based on the detected impact. A processing circuitry of the transaction card is coupled to the piezoelectric chip. The processing circuitry, upon powering on, is configured to enable data exchange between the transaction card and a terminal device for executing a card-based transaction at the terminal device. The data exchange is enabled only when a magnitude of the electrical pulse signal exceeds a threshold value, thereby preventing unwanted data transfer from the transaction card.

Abstract: Methods and systems for training artificial intelligence (AI)-based models using limited labeled data are disclosed. The method performed by a server system includes accessing a tabular dataset including tabular data that further labeled data and unlabeled data. Method includes generating labeled features including labeled numerical features and labeled categorical features based on the labeled data and generating unlabeled features including unlabeled numerical features and unlabeled categorical features based on the unlabeled data. Method includes determining, via a first transformer model, a contextual numerical embeddings based on the labeled numerical features and the unlabeled numerical features. Method includes determining, via a second transformer model, a contextual categorical embeddings based on the labeled categorical features and the unlabeled categorical features.

Abstract: The disclosure relates to methods and systems of generating geodata match classifications based on an ensemble of weak supervision-based match labels and geo-similarity models. The system may generate at least two match classifiers that are ensembled together. The match classifiers may include a location name classifier and a geo-similarity classifier. The location name classifier may generate a match classification that is based on a similarity of characters of the location names. The geo-similarity classifier may generate a match classification that is based on a proximity of the geolocations defined by the location names. The match classifications may be aggregated together to generate a geodata match classification.

Abstract: A method is described of managing service events in a distributed computing system. The distributed computing system comprises a plurality of computing nodes able to perform a service using a service process. The method takes place at one of the computing nodes. A service event is received or created. This service event is identified by a combination of a node identifier, a time element, and a local counter value. The local counter value represents a number of service events performed by a service process for a user since a last reset. The identified service event is then stored in a service process database according to node identifier and local counter values. The service process database is used to manage service events in the distributed system. Service events are removed from the service process database when no longer valid using the time element.

Abstract: The disclosure relates to methods and systems of generating matches between unmatched descriptors and known entities and training and using a machine learning-based match classifier (ML match classifier) to generate match classifications. For example, a system may access an unmatched descriptor having unstructured content and extract one or more data elements from the unmatched descriptor. The system may compare each of the extracted data elements with data records of known entities to identify candidate matches. The system may train and use the ML match classifier to validate the candidate matches. The ML match classifier may be trained based on labeled features derived from similarity metrics between two strings such as a name associated with the unmatched descriptor and a name of a candidate entity.

Abstract: A system has a datastore including a pro-rata digital wallet associated with a cardholder. The pro-rata digital wallet includes two or more payment card accounts. The system includes a processor programmed to receive an authorization request message from a point-of-sale terminal. The authorization request includes an identification number from a transaction device presented by the cardholder. The processor is programmed to determine whether the identification number corresponds to one of the payment card accounts associated with the pro-rata digital wallet and, if so, identify each of the payment card accounts associated with the pro-rata digital wallet. The processor is programmed to determine a pro-rata payment amount for each of the payment card accounts associated with the pro-rata digital wallet. Each pro-rata payment is based on an available balance of each of the payment card accounts relative to a total available balance for a combination of each of the payment card.

Abstract: A system is configured to retrieve a set of raw transaction data. A transaction categorization model is applied to the raw transaction data. The transaction categorization model infers a category from each transaction and labels each transaction with the inferred category. An entity recognition model is applied to the labelled transaction data. The entity recognition model extracts an entity from each transaction and labels each transaction with the extracted entity. The system generates a plurality of transaction streams from the labelled transactions based on the category and entity labels. The system also labels each transaction stream with either a loan label or a non-loan label based on an analysis of the types of transactions defining the transaction stream. The system trains a supervised-based neural network using the labelled transaction streams to generate a credit stacking classifier model.

Abstract: A system is configured to retrieve a set of raw transaction data. A transaction categorization model is applied to the raw transaction data. The transaction categorization model infers a category from each transaction and labels each transaction with the inferred category. An entity recognition model is applied to the labelled transaction data. The entity recognition model extracts an entity from each transaction and labels each transaction with the extracted entity. The system generates a plurality of transaction streams from the labelled transactions based on the category and entity labels. The system also labels each transaction stream with either a revenue label or a non-revenue label based on an analysis of the types of transactions defining the transaction stream. The system trains a supervised-based neural network using the labelled transaction streams to generate a revenue stream classifier model.