Abstract: The disclosure describes embodiments of systems, methods, and non-transitory computer readable storage media that enable network transactions between user accounts belonging to different network transaction platforms and unify user account modifications across user accounts on different network transaction platforms. For instance, the disclosed systems can cause two or more network transaction platforms to transmit and/or receive transactional values from one or more intermediary holding accounts upon receiving network transaction requests between user accounts belonging to the two or more network transaction platforms. In addition, the disclosed system can unify user account data on different network transaction platforms by modifying or updating the user account data (e.g., user attributes) by propagating schematized data messages to the one or more other network transaction platforms with instructions to modify or update the user attributes on other user accounts related to the user account.

Abstract: Machine learning models for fraud detection. The method includes receiving a schedule of weights, the schedule comprising a plurality of entries, each entry comprising a transaction value weight, a transaction volume weight, and a range of intervention rates; testing the at least one machine learning model using a holdout data set, resulting in a ranked transactions data set; and evaluating the performance of the at least one machine learning model by computing the weighted harmonic mean of the ranked transactions data set using the schedule of weights.

Abstract: A method for automatically recommending to a user of a software application one or more categories of a plurality of different categories of tax deductible expenses includes providing input data to a trained machine learning model and receiving output from the trained machine learning model based on the input data. The output includes a recommendation for the user that includes (i) one or more categories of the plurality of different categories of tax deductible expenses; and (ii) a plurality of examples of tax deductible expenses for each of the one or more categories. The method includes receiving feedback from the user on the recommendation and generating updated training data for the trained machine learning model based on the feedback.

Abstract: Provided are systems and methods for auto-performing short-term investments on an intermittent basis via a crypto-network and returning the principal and any interest before the account holder needs the money back. For example, a method may include executing a machine learning model on ingested data records to identify a temporary value that is idle in an account and a period of time that the temporary value is idle, displaying the determined temporary value, the period of time, and one or more recommendations of one or more blockchain networks, receiving authorization and a selection of a blockchain network from a user interface, installing a pre-programmed blockchain wallet on a blockchain ledger of the selected blockchain network, and triggering a transfer of funds from the account of the user to the pre-programmed blockchain wallet via a crypto-exchange server which converts the funds to cryptocurrency prior to the transfer.

Abstract: Provided are systems and methods for auto-performing short-term investments on an intermittent basis via a crypto-network and returning the principal and interest before the cash is needed. As an example, the method may include installing a blockchain smart contract on a blockchain ledger with read access to content stored on the blockchain ledger, establishing a communication channel between a monitoring engine and the blockchain smart contract, configuring the monitoring engine to identify stop conditions from content stored on the blockchain ledger, monitoring the blockchain ledger for updates to content stored on the blockchain ledger via the communication channel and detecting a stop condition based on an update to the blockchain ledger via the monitoring engine, and in response the detected stop condition, transmitting a request to the crypto-exchange server to return the funds to the external data source.

Abstract: The present invention relates to a system and method for providing restitution to a beneficiary when a package shipped by an originating shipper to a destination address, by way of a designated package transport carrier, is left unattended and damaged due to improper storage or exposure to inclement weather at the destination address prior to the package recipient taking receipt of the package. In an exemplary embodiment, a beneficiary is compensated, in accordance with a package repayment plan, when at least: a missing or damaged package report was created by the designated package transport carrier, the report indicates the package was delivered to the destination address during the plan enforcement period, and the originating shipper and the designated package transport carrier declined to provide a suitable remedy. Other embodiments include authorizing coverage for an address and package value, charging a transaction fee for authorizing coverage, and identifying fraud.

Abstract: Methods, systems, and apparatuses are described herein for the direct sharing and use of transaction data separately from transaction authorization processes. Transaction metadata associated with a transaction may be received and validated. Authorization information corresponding to the transaction may be received. The degree to which the transaction metadata is tested may be based on a predicted time of receipt of the authorization information. The transaction metadata and authorization information may be correlated. A computing device may determine whether to authorize the financial transaction based on the authorization information and the correlated transaction metadata. All or portions of the transaction metadata may be provided to one or more users after the transaction has been authorized or denied.

Abstract: A computer-implemented method includes: receiving an inquiry request message identifying a first payment transaction having a plurality of transaction parameters and a risk score, where the risk score is generated by a machine-learning model based on the plurality of transaction parameters; for each transaction parameter of the plurality of transaction parameters, perturbing a value of the transaction parameter and re-analyzing the first payment transaction with the machine-learning model to generate a perturbed risk score based on the perturbed transaction parameter; determining at least one impact parameter from the plurality of transaction parameters by comparing the perturbed risk scores generated for each of the plurality of transaction parameters; and generating an inquiry response message based on the at least one impact parameter.

Abstract: Platform-agnostic digital assistant methods and apparatuses are provided. The apparatuses and methods include a processor configured by a memory to receive user data from a storage containing informational contents. The processor is configured to establish a communication channel with an entity and utilize the communication channel to receive first information related to a user. The processor is configured to extract at least one user datum from the first information and modify the informational contents of the storage based on at least one of the user datum and the first information. The processor is further configured to initiate an action related to the user based on at least one of the first information, the user datum, and the informational contents.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for updating and managing hosted catalogs in a procurement system. A procurement system is provided comprising at least one live hosted catalog and at least one staged hosted catalog. Catalog update files are received into the system, and a data integration component validates and imports the catalog updates to the staged catalog, and an authorized buyer user is presented a summary of the update information and, upon an acceptance of the updates by the buyer user, the catalog update information is promoted to the live hosted catalog. In one embodiment a central catalog service maintains status information of the updates and coordinates workflow. In another embodiment, the system evaluates the update information and determines whether an approval is required.

Abstract: Systems and methods of reconfiguring machine learning models are disclosed. A method includes receiving, by a server computer, external data and determining, by the server computer, a machine learning model from a plurality of machine learning models, based on the external data. The plurality of machine learning models are in standby mode. The server computer configures an AI engine with the machine learning model. The method also includes receiving, by the server computer, a prediction request from a client computer, processing the prediction request with the AI engine to form a prediction response, and sending the prediction response to the client computer.

Abstract: Methods and systems for using machine learning to automatically determine a data loading configuration for a computer-based rule engine are presented. The computer-based rule engine is configured to use rules to evaluate incoming transaction requests. Data of various data types may be required by the rule engine when evaluating the incoming transaction requests. The data loading configuration specifies pre-loading data associated with at least a first data type and lazy-loading data associated with at least a second data type. Statistical data such as use rates and loading times associated with the various data types may be supplied to a machine learning module to determine a particular loading configuration for the various data types. The computer-based rule engine then loads data according to the data loading configuration when evaluating a subsequent transaction request.

Abstract: A method for processing a potentially fraudulent electronic payment transaction includes: receiving a first fraud detection rule configured to identify a potentially fraudulent electronic payment transaction; storing the first fraud detection rule in a fraud rules database; receiving a transaction request message; generating and storing a first case record associated with the first transaction in a case management database; receiving an updated fraud detection rule superseding the first fraud detection rule; applying the updated fraud detection rule to the first transaction to determine whether the first transaction does not satisfy the at least one updated fraud detection rule; and deleting the first case record from the case management database before the first transaction is further analyzed for fraud.

Abstract: A method of integrating electronic data including integrating a desktop such that the desktop includes information received from various sources. The information displayed may be analyzed by a business rule to prioritize what information is included in the desktop, and the information may include data from databases, recent member activities, planned future actions, and recommended future actions. The method also includes the ability to integrate and/or aggregate various data sources, such as databases. The combination of the data sources may be performed according to one or more business rules.

Abstract: A system includes collecting serial numbers over a period of time, and constructing a matrix indicating which digits have been used at which positions. For a second period of time, the system collects a second group of serial numbers and, for each of these serial numbers, identifies a feature of the serial number by comparing it against the matrix, and automatically updates the matrix with the digits and digit positions of the serial number. The features are received into an artificial intelligence model as training data. Further, the system collects a third group of serial numbers and, for each serial number of the third group, identifies a feature of the serial number by comparing it against the matrix. These features are then received into the artificial intelligence model, which determines a risk score. The matrix is then updated with the digits and digit positions of the serial number.

Abstract: The disclosed embodiments relate to systems and methods for matching orders for a financial product. A first order for a financial product is received. The first order includes a preference for a first order book. An order processer selects a first hardware match processor based on the preference. A first hardware match processor attempts to match the first order with a previously received order in the first order book. A second order for the financial product is received. The second order includes a preference for a second order book. The order processor selects a second hardware match processor based on the preference. A second hardware match processor attempts to match the second order with a previously received order in the second order book. The first and second hardware match processors use different matching algorithms.

Abstract: User devices are disclosed for managing a plurality of supplemental payment sources of a user. One method includes: generating and displaying a user interface prompting a user to input: an identifier of a primary payment source account for applying resources to transactions originating at one or more merchants, the primary payment source account being accounted for in a first data structure of a shared ledger and having its identifier linked with one or more supplemental payment source accounts; identifiers of one or more supplemental payment source accounts for applying resources to transactions originating at one or more merchants, the supplemental payment source accounts being accounted for in second and subsequent data structures of the shared ledger; and preference settings for applying resources of the primary payment source account and the supplemental payment source accounts to transactions, based on identities or categories of merchants involved in the transactions.

Abstract: Systems and methods are disclosed for least cost acquirer routing based on pricing models. One method comprises: receiving transaction-related information from a merchant, the transaction-related information including a payment network identifier of the payment network used in the initiated payment transaction; identifying the payment network used based on the payment network identifier determining the primary qualification criteria pertaining to the payment network used; determining an interchange rate and an interchange category based on the primary qualification criteria and the received transaction related information; determining a pricing model of an acquirer that yields the lowest fees applicable to the merchant based on one or more of, the transaction related information, the primary qualification criteria, and the interchange category; and transmitting the transaction-related information to the acquirer.

Abstract: Systems and methods involving computer-based processing for helping customers meet their minimum spend requirement for their introductory credit card offer are disclosed. In one embodiment, an exemplary computer-implemented method may comprise: receiving a total spending amount of a promotional credit card associated with an introductory credit card offer; determining a critical amount to satisfy the minimum spending amount of the promotional credit card; and causing to present a reminder on a screen of a user-associated computing device.

Abstract: Systems and methods for facilitating payment application provisioning and transacting are disclosed. According to one embodiment, a method for provisioning a token to a third party payment application on a mobile device may include (1) receiving a logon from a customer using a mobile application for a financial institution executed on a mobile device and a device identifier for the mobile device; (2) receiving a request to provision a token for a third party payment application; (3) authenticating the customer using the logon information and the device identifier; (4) provisioning a token for a payment device associated with the customer; and (5) providing the token to the third party payment application for transaction processing.