Abstract: A computer-implemented method for transmitting electronic query data related to various types of information or resources may include detecting user input on a website or other platform indicating permission to receive electronic data, causing display a widget or other user interface element that pre-fills the user input with query criteria, and requesting additional query criteria from the user to generate a complete query. The method may also include receiving available data including corresponding location or other relevant data for each available resource, determining a subset of data including recommended resources for the user based on the query location or other parameters, the initial query criteria, and the additional query criteria, and transmitting the subset of data to a graphical user interface on the user's device or other platform.

Abstract: Methods and systems are disclosed herein to recommend load rebalancing based on learned patterns of recurrence. In some aspects, the method receives a requested load usage from a user system and a load usage dataset. Each entry in the load usage dataset corresponds to an instance of load use. The method determines similar instances based on a respective amount and respective category of each entry. The method then clusters the similar instances into a first cluster and a second cluster based on frequencies of the similar instances. The method combines load uses corresponding to the first cluster into a first recurring load use and load uses corresponding to the second cluster into a second recurring load use. The method compares the requested load usage to the second recurring load use to generate a recommendation to the user system for rebalancing load usage.

Abstract: A method and related system operations for summarizing information includes determining a plurality of local explainability parameters for a set of inputs using a local explainability model for a prediction model. The method further includes generating a plurality of feature effect indicators for a target prediction and generating a plurality of phrases based on the plurality of feature effect indicators by using a text generation model. The method further includes generating a summarization using a large language model based on the plurality of phrases.

Abstract: Methods and systems for generating synthetic training data based on abandoned web activity data are described herein. In some aspects, the system determines that a user abandoned a user activity included in web activity data for the user. The system processes, using a first machine learning model, the abandoned web activity data to generate a probability for each entry in the abandoned web activity data. Each probability indicates a likelihood that the abandoned user activity would have been completed. The system generates a synthetic dataset that includes abandoned web activity with a probability above a threshold. The system uses the synthetic dataset to train a second machine learning model. The system tests the machine learning model using a testing dataset based on completed user activities.

Abstract: A method and related system perform operations to obtain data points in a feature space for a set of input records, determine explainability parameters for the data points and a prediction model using an explainability model, and determine a score associated with a candidate data point of the data points based on a first set of values and a second set of values determined with the explainability parameters. Some embodiments may select the candidate data point based on a result indicating that the score satisfies a threshold and store, in a memory, an indication of a candidate record associated with the candidate data point.

Abstract: Systems and methods for deploying machine learning models trained on synthetic data generated based on a predicted future data drift are described herein. In some aspects, the system analyzes data profiles that include snapshots of data from different points in time from the same data stream to predict a future data drift. The system generates synthetic data based on the previous data profiles. The system determines, based on a first and second data profile, that a first data drift exceeds a threshold and updates a machine learning model. The system determines a predicted data drift and generates a synthetic snapshot of the data stream corresponding to a time in the future. The system generates a speculative machine learning model from updating the first updated machine learning model based on the synthetic snapshot. The system deploys the speculative machine learning model to replace the first updated machine learning model.

Abstract: A system and method for enhancing searching capabilities is disclosed. The system and method can receive an image and metadata associated with the image. An intensity map of a grayscale vector may be generated corresponding to the image. An HTML code snippet may be placed at a coordinate location within the image and a browsing activity associated with the image may be detected. The HTML code snippet may be activated in response to detecting the browsing activity at a coordinate location. An interactive page may be rendered on a user interface, the interactive page including the image and the metadata associated with the image. The code snippet output may be correlated with the metadata to generate image browsing track data. A user browsing profile may be generated including the image browsing track data.

Abstract: Embodiments are directed to methods and techniques for providing power via piezoelectric components on contactless cards.

Abstract: Systems and methods are disclosed for the deposit, withdrawal, and reuse of currency for transactions. According to disclosed embodiments, an intelligent teller machine (ITM) is configured to receive currency as payment for a transaction, to calculate and dispense any change due, and to request that the net value of the transaction (e.g., the revenue) be deposited into the financial account of the business. The currency received by the ITM is also available to make change for future purchase transactions.

Abstract: Disclosed herein are systems and methods of automated teller machine (ATM) management. The method can include receiving, from an ATM, an operating log from an out-of-band management chip. The method can further include determining, from the operating log, that the ATM is in an out-of-service state. The method can further include transmitting instructions to the out-of-band management chip to capture a system image of the ATM. In response, the method can include receiving the system image of the ATM from the out-of-band management chip and diagnosing a fault in the ATM based on the system image. The fault in the ATM can be the fault which caused the ATM to be in the out-of-service state. Finally, the method can include transmitting instructions for one or more corrective actions to the out-of-band management chip. The corrective actions can remedy the fault in the ATM.

Abstract: A system including: one or more processors; a memory storing computer program code that controls the one or more processors to: receive usage metrics associated with a first application; determine whether the first application comprises a cyclic usage pattern, a batch usage pattern, or a non-cyclic usage pattern; select a scaling technique based on the determination; and automatically scale the first application with the selected scaling technique. The system may determine that at least one virtual machine should be added to a first plurality of virtual machines in response to a resource usage of an application exceeding a maximum usage allocation and determine that at least one virtual machine should be removed to the first plurality of virtual machines in response to a minimum usage allocation exceeding the resource usage of the first plurality of virtual machine instances.

Abstract: Systems and methods are provided for group bill payment comprising creating a secure group bill payment account associated with a plurality of group members. The group bill payment account may be configured to receive information via a network from the plurality of group members; permit a group member to manage the group bill payment account following an authentication process; and transmit a group payment to a provider. Systems and methods may further comprise receiving instructions from a group member to create a rule for requesting payment, the bill being from a provider and associated with group members; receiving the bill issued by the provider; determining a charge based on the bill and the rule; sending a payment request based on the charge; receiving a deposit into the group bill payment account; transmitting a group payment; and sending a notification.

Abstract: Aspects described herein may use behavioral biometric data to authenticate an individual that requests performance of an action related to a financial account. In response to the request, challenge questions relating to recent transactions conducted with the financial account may be generated. The challenge questions may be provided to the individual and may prompt the individual for audile response and/or touch input responses. Behavioral biometric data may be extracted from the responses and may be used to determine a likelihood the individual is an authorized user of the account.

Abstract: A device receives, from multiple cameras, streaming video data associated with multiple vehicles and provides the streaming video data to a user device associated with a user. The device receives, from the user device, a request to control a first camera and provides, to the user device, first streaming video data associated with the first camera. The device receives, from the user device, a camera control command for the first camera and causes the first camera to perform an action. The device receives updated first streaming video data from the first camera and provides, to the user device, the updated first streaming video data. The device receives, from the user device, information identifying a first vehicle in the updated first streaming video data and identifies first augmented reality vehicle information associated with the first vehicle. The device provides the first augmented reality vehicle information to the user device.

Abstract: Systems, methods, and computer-readable media for providing accurate images of cards. An application executing on a mobile device may receive authentication credentials for an account, determine a card associated with the account, and determine a card manufacturer identifier (CMID) of the card. The application may receive, from a digital asset management system based on the CMID, a plurality of metadata attributes of the card and one or more images of the card. The application may determine, based on the metadata attributes and attributes of the mobile device, a first orientation of the card to enable near-field communication (NFC) data transfer between the card and the mobile device. The application may select a first image of the card. The application may generate a graphical user interface (GUI) including the first image and an indication specifying to tap the card to the mobile device according to the first orientation.

Abstract: A computer implemented method, system, and non-transitory computer-readable device that may be used in a remote deposit environment. A plurality of differing neural networks, such as customizable neural networks, are selected, based on an architecture and features of the data field, to extract data from specific data fields on a document. The selected customizable neural networks are trained by historical or synthetic data corresponding to the data fields. Upon receiving, from a neural network Optical Character Recognition (OCR) system, a selected first trained customizable neural network model and at least a second selected trained customizable neural network model, the data fields are extracted, based on a series or parallel configuration of the customizable neural networks, and the extracted data communicated to a remote deposit process.

Abstract: The present disclosure includes systems and methods enabling secure workflows by receiving an electronic event authentication message from an initiator device, where the electronic event authentication message comprises a user profile identifier, and an entity identifier. A first device-specific actions-sequence token is generated for an actions-sequence session to execute a device-specific instance of at least one automated processing actions-sequence. A workflow request message is received from the initiator device that includes the user profile identifier and the entity identifier, and a second device-specific actions-sequence token is generated. Where the first and second device-specific actions-sequence tokens match, the actions-sequence session is executed and a criterion update in response to the actions-sequence session is produced. The criterion update may then be transmitted to the initiator device.

Abstract: Embodiments disclosed herein generally relate to a system and method for initiating an interactive chat via HTTP request. A web server of an organization computing system receives the HTTP request from a web client executing on a remote client. The HTTP request is triggered by a selection of a dialogue request embedded in an electronic mail message. The web server transmits an API call to a back-end computing system of the organization computing system based on information included in the HTTP request. The back-end computing system parses the API call to identify a user identifier corresponding to a user of the remote client device and a request identifier corresponding to the selected dialogue request embedded in the electronic mail message. The back-end computing system initiates the interactive chat via a text-based communication channel. The back-end computing system generates and transmits an electronic message comprising a response to the dialogue request.

Abstract: A computer vision card reader and/or point of sale device is described. The device is configured to sense when a user inserts a card into a card reader and to determine when a user departs or is about to depart from the device without retrieving the card. The device may issue an audible or visible alert to the user, reminding the user to retrieve the card. The device may additionally send a notification to a mobile device associated with the user that reminds the user that he has left a card at the point of sale. In some embodiments, message sent to the user contains a code and, upon entry of the code, the point of sale or card reader device returns the card to the user.

Abstract: The methods and systems described herein improve upon existing deep linking concepts, by creating links directed to a feature registry which may then serve the user's need of selecting and accessing a given feature. The feature registry may provide customized features that may populate a feature template in a user interface (e.g., of a feature registry application) on a local device. This population may occur in both a real-time (e.g., based on a continuously updated machine learning model) and modular fashion. For example, the system and methods may generate customized content on a website or mobile application through a hyperlink by filtering available features on a feature registry based on the identity of the user, the information from the user profile, and the description of the hyperlink content.