Abstract: Disclosed embodiments may include a system that may receive an indication that a user is accessing an ATM, receive, from the ATM, average session duration data over a predetermined period, generate, using a machine learning model, a busyness score for the ATM based on the average session duration data over the predetermined period, and determine whether the busyness score for the ATM exceeds a busyness score threshold. When the busyness score for the ATM does not exceed the busyness score threshold, the system may cause the ATM to present, via a first graphical user interface, a default ATM experience. When the busyness score for the ATM exceeds the busyness score threshold, the system may cause the ATM to present via, a second graphical user interface, a busy ATM experience.

Abstract: Embodiments are generally directed to systems, device, and techniques to utilize a uniform resource locator to exchange money.

Abstract: A method of performing an intention classification with a first large language model included in a first agent included in a multi-agent system, the first large language model configured to receive the input message as a text input, the intention classification associating an intent of the request with a corresponding action. Sending, from the first large language model to an action router, a response including a key that uniquely identifies an action handler from among a plurality of available action handlers, the action handler designated to coordinate operations of the multi-agent system to complete the corresponding action with a workflow defined by the selected action handler. Completing the workflow, at least in part, with the designated action handler generating function calls directed to the multi-agent system and processing API responses received from the multi-agent system to complete tasks included in the predetermined set of tasks.

Abstract: A method for managing value attribution for a data system includes obtaining, by the data system, order data associated with a plurality of data vendors, wherein the order data comprises variables about client devices, in response to obtaining the order data: applying the variables in the order data to a classification model to obtain fraud prediction models, performing an explainable mechanism on the fraud classification predictions using a shapley additive explanation (SHAP) to obtain localized SHAP values, applying a set of custom transformations to obtain normalized features, applying a value attribution algorithm on the normalized features using vendor information associated with the order data to obtain vendor values each associated with one of the plurality of data vendors, and performing a vendor remediation on the plurality of data vendors based on the obtained vendor values.

Abstract: Systems and methods for transforming an electronic portfolio. A system includes an electronic crossing platform that receives data defining trade orders of the electronic portfolio during an initial time period; compares portions of the data to determine an imbalance of the trade orders remaining after the initial time period and receives, during a final time period, a final trade order from a fund agent device to offset the remaining imbalance. The platform receives, after the final time period, a benchmark value of the electronic portfolio from a fund device; compares the final trade order with the remaining imbalance to determine an adjustment value; converts the benchmark value to a final value by applying the adjustment value to the benchmark value; and transforms the electronic portfolio into the transformed portfolio by creating paired buy and sell orders among the trade orders received during the initial time period at the final value.

Abstract: A system comprises a processor configured to receive user criteria associated with an operation and to obtain a plurality of segment candidates from a plurality of sources, each source configured to provide a segment of the operation that corresponds to a respective segment candidate obtained from said source. The processor is configured to determine a plurality of operation structure candidates for the operation. Each operation structure candidate is determined based on aggregating a respective subset of the plurality of segment candidates. The processor is configured to determine a priority for each operation structure candidate based on prioritization rules stored in memory of the system and based on the user criteria. The processor is configured to communicate an output indicating one or more of the operation structure candidates for the operation. The output is based on the priority.

Abstract: The disclosed embodiments relate to implementation, such as by a message processing system architecture, of a message handling system and/or protocol which mitigates optimistic messaging behavior. As used herein optimistic messaging behavior may at least refer to the transmission, in whole or in part, of a message, or of one or more messages of a sequence thereof, to a receiving system, such as the system implemented by the disclosed embodiments, prior to the sender determining that the message(s) is/are desired, alone or in conjunction with subsequently canceling or otherwise invalidating the message(s) once it has been determined that it is not desired. The disclosed embodiments mitigate such behavior by detecting and taking action with respect to these types of messages to deter optimizing behavior which may or may not be manipulative, while maintaining reliable message handling under increasing processing loads with minimal impact on users being able to send messages to the system.

Abstract: A multivariate predictive system processes usage based data that includes a database engine that provides access to a plurality of database management systems that mine diverse sources of usage based data. A digital filter selectively filters data streams that include usage based data. A sampler automatically divides the filtered data into sample groups and stores the sample groups in a memory. The sampler divides the filtered data according to insurance rating variables processed by a processor programmed to underwrite an insurance product and rate that insurance product. Some samplers store the divided filter data in a local memory. A multiplier multiples rating factors preprogrammed with the insurance rating variables with a base rate of insurance to determine an insured's insurance premium.

Abstract: In some examples, a system may determine a date on which a balance of a user account is expected to fall below a threshold based on analyzing at least one of: the balance of the user account over time, or historical transactions of the user over time. The system may determine an amount for an item purchased, or intended to be purchased, by the user, and may cause the user computing device to present, prior to the date, a suggestion to request financing for the item. In response to a request to finance the item, the system may cause the user computing device to present a graphical user interface (GUI) that includes offers for financing. The system may receive, from the user computing device, via the GUI, a selection of a first offer, and may send an instruction to cause a transfer of funds to the user account.

Abstract: The invention relates to a computer-implemented system and method for receiving at a business an electronic person to business (P2B) payment from an individual. The method may comprise the steps of contacting an individual having a demand deposit account (DDA) to request the P2B payment in an amount that is due to the business; providing a designated electronic address for the business for receiving the P2B payment; identifying a reference number that is associated with the P2B payment; requesting the individual to use a P2B payment server to make the P2B payment from the individual's DDA account to the designated electronic address, wherein the P2B payment is associated with the reference number; monitoring the P2B payment server in real time to confirm receipt of the P2B payment; and using the reference number to apply the received P2B payment to the amount that is due to the business.

Abstract: A transaction processing system includes a transaction processing module configured to receive first information associated with a first proposed transaction, retrieve second information associated with at least one prior transaction that is associated with the first proposed transaction, and calculate a time-decayed algorithm using the second information to generate third information. The transaction processing system also includes a weighting module communicably coupled to the transaction processing module, wherein the weighting module is configured to receive the third information from the neural-based processing module, apply a weighting factor to the third information to generate fourth information, and calculate at least one processing algorithm using the first information and the fourth information to generate an output. The output of the weighting module is used by an additional transaction processing module to determine whether the first proposed transaction is fraudulent.

Abstract: A method, performed by a server, of managing a non-fungible token (NFT) for content, is provided. The method includes, in response to receiving a request to issue an NFT for target content from a first electronic device of a first user who has generated the target content, generating basic metadata on the target content, uploading the generated basic metadata to a target folder generated in an interplanetary file system (IPFS), generating first ownership metadata including a content identifier (CID) of the uploaded basic metadata, obtaining a first CID of the target folder with the first ownership metadata uploaded to the target folder, and linking the obtained first CID of the target folder to an NFT uniform resource identifier (URI) of the target content.

Abstract: Systems, methods and user interfaces are provided for order matrix management and highlighting. Market data may be arranged in a matrix where the market data may be highlighted and/or otherwise presented to provide further information to a user. In some cases a computer system may include a computer-readable medium containing computer-executable instructions that, when executed by one or more processors, cause a computing device to receive market data for a financial instrument. The computer system may further process instructions to identify pending orders that may result in a cross trade, such as with trades entered by a trader or between members of a same business organization. The computer system may further process instructions that cause the computer system to generate a user interface that highlights which of the pending orders that may result in a cross trade.

Abstract: Systems and methods are disclosed for determining the efficacy of an autonomous vehicle driving system in exhibiting safe driving behavior during test track scenarios. Testing parameters eliciting autonomous vehicle driving system behavior may be chosen for the test track scenario. The autonomous vehicle driving system may be tested in the test track and autonomous vehicle driving system behavior may be observed in response to the presentations of testing parameters. A safe driving score may be calculated for the autonomous vehicle driving system based on measured autonomous vehicle performance and operational data generated responsive to the presentation of testing parameters in the test track. A benchmark insurance premium may be calculated for an autonomous vehicle driving system based on the calculated safe driving score.

Abstract: Disclosed are methods and systems for automatically configuring financial product offerings. An example method includes: receiving, by a computer system, a graph model representing a plurality of permutations of definition provisions of a financial product; translating at least a subset of the graph model into definitions of a plurality of business objects; translating the definitions of the plurality of business objects into definitions of a plurality of services to be implemented by an offering of the financial product; receiving, via a user interface, a plurality of service configuration options; applying the plurality of service configuration options to the definitions of the plurality of services; and generating, based on the definitions of the plurality of services, service configuration data for the offering of the financial product.

Abstract: Methods, systems, and computer program products for learning continuous embedding space of real time payment (RTP) transactions are provided. A method may include receiving RTP data including a plurality of attributes, including a sender and a receiver. One attribute is selected as a target attribute. The remaining attributes are input into a first machine learning model (e.g., NLP model), comprising at least one embedding layer and one hidden layer, which is trained to predict the target attribute. After the model is trained, each of the remaining attributes are converted to a first vector using the at least one embedding layer of the machine learning model to form a first set of vectors. The first set of vectors are stored and subsequently input into a second machine learning model to perform at least one second task different than the first task.

Abstract: Systems and methods for transforming an electronic portfolio. A system includes an electronic crossing platform that receives data defining trade orders of the electronic portfolio during an initial time period; compares portions of the data to determine an imbalance of the trade orders remaining after the initial time period and receives, during a final time period, a final trade order from a fund agent device to offset the remaining imbalance. The platform receives, after the final time period, a benchmark value of the electronic portfolio from a fund device; compares the final trade order with the remaining imbalance to determine an adjustment value; converts the benchmark value to a final value by applying the adjustment value to the benchmark value; and transforms the electronic portfolio into the transformed portfolio by creating paired buy and sell orders among the trade orders received during the initial time period at the final value.

Abstract: An insurance server for using a tokenized icon to provide an insurance quote or submit an insurance claim may include a processor programmed to receive an image from a user application, and data associated with the image, wherein at least a portion of the obtained data is associated as metadata with the tokenized icon. The processor may instruct the user application to use an icon associated with the tokenized icon as a first graphical object, and to modify, in response to an association of the first graphical object with a second graphical object in the user application, the metadata of the tokenized icon based upon data associated with the second graphical object. The processor may transmit the virtual quote or proposed insurance claim to the user application, the virtual quote or proposed insurance claim being based upon the modified metadata. As a result, the online customer experience may be enhanced.

Abstract: Systems and methods for identifying and providing unfulfilled services to a user of a provider institution mobile application are provided. A method includes: identifying an unfulfilled service of the user of the provider institution mobile application based on an indication that the user has a pending service that requires further action on behalf of the user; scanning a digital calendar of a mobile device of the user hosting the provider institution mobile application based on receiving a user input to access the digital calendar; determining an availability of the user based on scanning the digital calendar; identifying a current location of the user during the determined availability; determining a plurality of service locations near the identified current location of the user during the determined availability; and prompting the user to visit an identified service location from the plurality of service locations.

Abstract: An electronic trading system is configured to create speculative orders based on real orders. The speculative order differs from the real order by the price, quantity, or the type of financial instrument. The match engine chooses one or more speculative orders in an attempt to predict the next real order. Even though processing multiple trades at the same time is impossible, the use of speculative orders can permit the match engine to perform the calculations involved with the trade and generate the messages associated with the trade ahead of time. If the prediction was correct and the next order received by the match engine corresponds to one of the speculative orders, some of the matching activity has already been performed. This in effect, allows the match engine to process trades more efficiently and increases the total trading volume that can be handled by the electronic trading system.