Abstract: A method for location-dependent determination comprises: determining, with one or more processors, a geographic location of a user's electronic device using first data; in response to determining the determined geographic location is insufficient for performing a location-dependent determination, requesting second data to determine an updated geographic location of the user's electronic device; performing, with an Application Programming Interface (API), the location-dependent determination based on the updated geographic location; and completing, with the API, a transaction using the location-dependent determination.

Abstract: Disclosed herein are systems and methods for identifying and transmitting electronic requests to a suitable service provider. In one method, a server receives, from a computing device, a request to verify data via at least one service provider; executes a first computer model to identify a likelihood of verification success of the data; responsive to the likelihood of verification success satisfying a threshold, executes a second computer model to determine a service provider to transmit the request based on a first attribute associated with the data, a type of verification associated with the request, and a second attribute associated with the set of service providers and an impact value associated with each service provider; and responsive to determining the service provider from the set of service providers, transmitting, by the processor via an application programming interface, the data to the service provider.

Abstract: A reader device for attachment to a smart device comprising a display, the reader comprising an antenna, processing and reading circuitry, and a communications module, wherein the antenna, the processing and reading circuitry, the processor and the communications module are coupled to each other, and whereby the antenna encloses said display. When a card is tapped on the display, the antenna receives a signal and transmits the signal to the processing and reading circuitry. The processing and reading circuitry processes the signal to produce data, and the produced data is transmitted to a device external to the reader device by the communications module.

Abstract: A method and apparatus for a certificate authority system providing authentication to a plurality of devices associated with an organization are described. The method may include receiving, at the certificate authority system, a request from a device to sign authentication information of the device, wherein the device is associated with the organization. The method may also include sending a challenge to the device to perform an action with a system other than the certificate authority system, and receiving the response to the challenge from the device. Furthermore, the method may include verifying that the response was generated correctly based on the challenge, and signing the authentication information of the device with one or more keys of the certificate authority system as an authentication of an identity of the device.

Abstract: A method and apparatus for fraud detection during transactions using identity graphs are described. The method may include receiving a document image for detecting whether an identity document depicted within the document image is fraudulent. The method may also include extracting data associated with the document image to generate extracted data. The method may also include processing, by a single machine learning model, subsets of the decoded image data used as corresponding inputs to each of a set of machine learning model backbones of the single machine learning model that generate one or more intermediate signals indicative of whether a subset of the extracted image data input into said each machine learning model backbone is associated with a fraudulent identity document.

Abstract: Systems and methods for implementing a machine learning loan portfolio loss forecasting system are provided. A current state of active loans of a loan portfolio during a first time period of a set of time periods may be determined. For each of the set of time periods, a roll rate of the active loans from each delinquency state to a subsequent delinquency state may be determined based on historical data of the loan portfolio. The machine learning model may then, iteratively, for each subsequent time period, determine a percentage of the active loans that will transition to each of the set of delinquency states during the subsequent time period based on a current state of the active loans during a previous time period and the roll rate from each delinquency state to a subsequent delinquency state for the subsequent time period.

Abstract: Described herein are systems and methods for predicting a metric value for an entity associated with a query node in a graph that represents a network. In embodiments, using a user's profile as the query node, a metric about that user may be estimated based, at least in part, as a function of how well connected the query node is to a whitelist of “good” users/nodes in the network, a blacklist of “bad” users/nodes in the network, or both. In embodiments, one or more nodes or edges may be weighted when determining a final score for the query node. In embodiments, the final score regarding the metric may be used to take one or more actions relative to the query node, including accepting it into a network, allowing or rejecting a transaction, assigning a classification to the node, using the final score to compute another estimate for a node, etc.

Abstract: In one aspect, a method of detecting database anomalies, includes reading historical data in a destination database at an end of a data pipeline, determining bounds including an upper bound and a lower bound based on the read historical data, reading current data for a first specified time period in the destination database, responsive to determining the upper or the lower bound is exceeded, determining database transactions that caused the exceeding, and transmitting alerts to owners of the database transactions.

Abstract: A method for generating a user interface includes: receiving a user request to access a software platform, the user request being associated with a user identifier; generating a user context based on the user request, the user context including a user profile associated with the user identifier; loading a data structure representing a user interface layout, the data structure including a plurality of viewport nodes, each of the viewport nodes being associated with one or more child nodes; selecting, by a computer system, a first child node from one or more child nodes of a first viewport node of the plurality of viewport nodes based on the user context to generate an evaluated data structure including a plurality of evaluated viewport nodes, each of the evaluated viewport nodes having at most one child node; and generating a customized user interface based on the evaluated data structure.

Abstract: Embodiments herein use transfer learning paradigms to facilitate classification across entities without requiring the entities access to the other party's sensitive data. In one or more embodiments, one entity may train a model using its own data (which may include at least some non-shared data) and shares either the scores (or an intermediate representation of the scores). One or more other parties may use the scores as a feature in its own model. The scores may be considered to act as an embedding of the features but do not reveal the features. In other embodiments, parties may be used to train part of a model or participate in generating one or more nodes of a decision tree without revealing all its features. The trained models or decision trees may then be used for classifying unlabeled events or items.

Abstract: Methods, systems, and computer readable medium are provided for generating, by a secure processor, a plurality of configurable data entry elements configured into a webpage, receiving sensitive data entered via the plurality of configurable data entry elements during a user data entry session, generating a hidden controller iframe in the webpage, aggregating, by the hidden controller iframe, the sensitive data across the plurality of configurable data entry elements, and directing aggregated sensitive data to the secure processor hosted by a first server separate from a second server hosting the webpage.

Abstract: Methods, systems, and media are provided for enabling encryption key distribution when a processor is in offline mode. When offline, key distribution servers can distribute private/public key pairs in place of the processor. The servers can distribute a private key to a first server for encryption of data and a public key to the processor, when it is online, to decrypt the data.

Abstract: In an example embodiment, information about one or more failed payment attempts via an electronic payment processing system is obtained. One or more features are extracted from the information. Then, for each of a plurality of potential candidate retry time points, the one or more features and the potential candidate retry time point are fed into a dunning model, the dunning model trained via a machine-learning algorithm to produce a dunning score indicative of a likelihood that a retry attempt at an input retry time point will result in a successful payment processing. The dunning scores for the plurality of potential candidate retry time points are used to select a desired retry time point. Then the electronic payment processing system is caused to attempt to reprocess a payment associated with one of the failed payment attempts at a time matching the desired retry time point.

Abstract: A method and apparatus for hard deletion of user data are described. The method may include receiving a request from a user computer system to delete user data. The method may also include determining a unique user identifier associated by a system with a user making the request. The method may also include determining whether a data partition, in which data generated by a job or subsystem of the computer system is stored, is predicted to contain a record having the unique user identifier. Then, the method may include searching, when the data partition is predicted to contain a record having the unique user identifier, data records stored in the data partition for a user data record based on the unique identifier, and performing a hard deletion of the user data record from the partition when found during the searching.

Abstract: A method and apparatus for a commerce platform providing proof of application ownership of a network distributable application are described. The method may include receiving a request to approve an application developed by a merchant system, wherein the application includes an application programming interface (API) component, a software development kit (SDK) component, or a combination thereof provided by the commerce platform to the merchant system. The method may also include generating a unique identifier (ID) for the application to be included as metadata within the application. Furthermore, the method may include obtaining, from an application information system, data describing the application, and extracting an ID from metadata in the data obtained by the application information system.

Abstract: A method and apparatus for generating and using secure sharded onboarding user interfaces are described. The method may include determining, based on account type of a merchant account being onboarded for a merchant by a first user, that information for a user type associated with a second user associated with the merchant is to be collected to satisfy minimum merchant account compliance requirements. The method may also include allocating a person object in an accounts data store maintained by the commerce platform system, the person object associated in the accounts data store with the merchant account. Furthermore, the method can include generating a secure link and transmitting the secure link to the second user, the secure link resolving at the commerce platform system and comprising a unique identifier that is associated with the person object.

Abstract: A method and apparatus for managing liquidity when processing transactions are disclosed. In some embodiments, the method is implemented by a computing device and comprises: receiving data for a plurality of transactions; continuously reading in and aggregating, with an aggregator implemented at least partially in hardware of the computing device, transactions to produce one or more netted currency positions based on a plurality of properties of the transactions and on a plurality of netting constraints; generating one or more tasks, using a trade generator implemented at least partially in hardware of the computing device, to route cash movements as one or more batched fund transfers based on one or more trading policies; and sending the one or more tasks via network communications to one or more entities to execute the batched fund transfers.

Abstract: In an example embodiment, a solution is provided that aggregates records as they are submitted to a third party (on the write path) rather than performing a real-time aggregation when a request is processed that needs the aggregation (read path). More particularly, in an example embodiment, a caching layer is introduced that avoids having to read all usage events to compute an aggregation when a request is received for aggregated data. The caching layer maintains values for various metrics that require aggregation.

Abstract: A magnetic reader head assembly includes a magnetic reader head compartment, a frame and an elastic component. The magnetic reader head compartment comprises electronic and mechanical components of the magnetic reader head. The frame has a front side and a back side and has a footprint matching the footprint of the magnetic reader head compartment. The front side is configured to attach to a back wall of the magnetic reader head compartment while allowing the magnetic reader head compartment to move out or retract from the frame. The elastic component is configured to be placed at the back side of the frame and to push the frame out in order to press the magnetic reader head compartment against a magnetic card stripe.