Abstract: Systems and methods for executing resource availability notifications to user systems are described. In some aspects, the system receives, for a first plurality of user systems, a first plurality of user profiles and a plurality of resource availability values. Each user profile includes values for a set of features. The system processes a first machine learning model which generates resource availability values from the set of features and extracts an explainability vector. The system uses the explainability vector to generate an embedding map that translates feature values into a corresponding embedding in an embedding space. The system encodes a second plurality of user profiles and processes the resulting user profile vectors using a second machine learning model to generate clusters of user profile vectors. The system selects a cluster from the clusters of user profile vectors and determines user systems corresponding to the cluster for executing resource availability notifications.

Abstract: Disclosed herein are system, method, and computer program product embodiments for a customer records management translation extension. A computer system receives customer data comprising a first name, last name, an email address, and a phone number from a front-end interface of an agent workstation. Based on the customer data, the computer system obtains one or more customer objects from a customer object database, wherein each of the customer object comprises a customer identifier. The computer system selects the customer object that best matches the customer data and obtains a customer lead identifier from the customer object database that corresponds to the customer identifier of the selected customer object. Based on the customer lead identifier, the computer system obtains a lead object from a lead object database and generates a link to the lead object. Finally, the computer system transmits the link to the front-end interface of the agent workstation.

Abstract: A system and method for generating offers is disclosed. The system and method can receive a identifier identifying a given item. A list of alternative inventory items may be generated for an item. A plurality of merchant and customer historic deal metrics may be determined based on past purchases for each of the alternative inventory items. A first and second cluster of data points may be generated based on the plurality of merchant and customer historic deal metrics. An overlap region between the first cluster and the second cluster may be determined. A data point from amongst the data points within the overlap region may be selected. An offer may be generated for the given item based on the selected data point. The offer may be transmitted to the client device for display on a graphical user interface (GUI).

Abstract: Systems and methods for enhanced security to log in to a mobile application are provided. A short-range communication antenna of a mobile device can receive a cryptogram from a contactless card, and a processor of the mobile device can verify the cryptogram to identify a customer account associated with the contactless card and verify that a phone number of the mobile device is associated with the customer account. Then, a user interface device of the mobile device can receive enhanced security input data, and the the processor of the mobile device can verify that the enhanced security input data matches enhanced security record data associated with the customer account. When the cryptogram, the phone number of the mobile device, and the enhanced security input data have been verified, systems and methods disclosed here can log in to a mobile application running on the mobile device to access the customer account.

Abstract: Systems and methods related to a variable non-fungible token that dynamically update metadata during blockchain functions. A variable non-fungible token comprises a non-fungible token that is minted with an indication of a non-transferable ownership wallet (e.g., a digital wallet for which the non-fungible token is minted for), a non-transferable smart contract address that has permissions for updating metadata for the variable non-fungible token, and a metadata property threshold based on a specific user corresponding to the digital wallet.

Abstract: Methods and systems are described herein for minimizing resource expenditure during model training using user-defined constraints in sample selection. A system may obtain user-defined target parameter values for data labeling, a user input indicative of a value added per unit of model performance improvement, and a dataset (e.g., unlabeled samples). The system may select a first subset of the dataset and may transmit a request for labeling the samples. The system may receive a first training dataset comprising label data and the samples of the first subset. The system may train a machine learning model using the first training dataset and generate a margin curve. Based on the margin curve, the system may determine whether an amount of resource usage exceeds value added and responsive to determining that it does not exceed the amount of resource usage, select a second subset of the dataset.

Abstract: In some implementations, a system may receive dependency indicators associated with a plurality of cloud-based applications and receive change indicators associated with changes to one or more first applications of the plurality of cloud-based applications. The system may receive an indicator associated with an incident ticket based on a problem with a second application of the plurality of cloud-based applications. The device may determine at least one of the change indicators associated with the incident ticket based on dependencies between the one or more first applications and the second application and based on a difference between a time associated with the incident ticket and a time associated with the at least one of the change indicators. The system may, based on determining the at least one of the change indicators, transmit a command to rollback at least one of the changes or to rollforward at least one change.

Abstract: A method may include a obtaining a first data model instance comprising an identifier string and. a set of attributes associated with a set of attribute name strings. The method may include obtaining an ontology graph that includes a first label, a second label, and an association between them. The method may include using a prediction model to select the first label based on the first data model instance and determining the second label based on the relationship. The method may include determining a selected set of labels that includes the first label and the second label to associate with the first data model instance. The method may include associating the selected set of labels with the first data model instance in a dataset that includes a plurality of records, where each record is associated with a different data model instance.

Abstract: According to certain aspects of the disclosure, non-transitory computer readable media, systems and methods are disclosed for creating and executing test scenarios for automated testing of web pages. A computer system, for example, may perform operations including: recording one or more actions performed by a user on a web page, the one or more actions resulting in a web page element being displayed in the web browser application, recording an identifier of the web page element, in response to detecting a user input indicating a selection of the web page element, and recording a characteristic of the web page element; and generating, by the testing extension, a test scenario specifying a testable outcome resulting from the one or more actions, the testable outcome being an occurrence of an element having the identifier and the characteristic.

Abstract: Disclosed herein are system, method, and computer program product embodiments for training and deploying a machine learning model to generate an assessment of risks and mitigations in response to a novel initiative request. After generating labeled data from a corpus of prior risk assessments, a machine learning model may be trained to programmatically generate a risk assessment in response to a novel initiative request. A risk auditor may subsequently review the risk assessment generated using the machine learning model to provide various feedback reflecting the accuracy of the risks and mitigations. The machine learning model may then be retrained based on the feedback provided by the risk auditor to provide more accurate risks and mitigations in response to future initiatives.

Abstract: The disclosed technology involves autonomously identifying goals and sub-goals from a user utterance and generating responses to the user based on the goals and sub-goals.

Abstract: Systems and methods for uses and/or improvements to using artificial intelligence applications with large datasets. In particular, systems and methods for enriching data structures (e.g., data structures comprising user profile data) with additional data structures (and values thereof) from accessible data from a plurality of other users based on identifying relevant data to use for enriching the data structures using detected metadata correlations.

Abstract: Disclosed embodiments may include a system for measuring document legibility. The system may automatically receive document image data from a user device. The system may then process the image data using optical character recognition to create language data containing a plurality of words. The system may then obtain an overall number by counting the plurality of words in the language data. The system may then identify and count the common words within the plurality of words by comparing the plurality of words to words in a database. A score may be obtained by dividing the common word number by the overall number. The score may then be compared to a legibility threshold. If the score is below the threshold, the system may determine the document is illegible. If the score is above the threshold, the system may determine the document is legible.

Abstract: A method for query optimization may include capturing a proposed database query input into a user interface. The method may further include providing the proposed database query to a machine-learning model. The machine-learning model may have been trained, using one or more gathered and/or simulated sets of query execution overhead data and one or more gathered and/or simulated sets of database queries, to determine a potential execution overhead of a database query and output a query execution score. The method may further include outputting, by the machine-learning model, the query execution score based on the proposed database query. The method may further include determining that the query execution score exceeds a query execution score threshold. The method may further include triggering a corrective action based on the query execution score exceeding the query execution score threshold.

Abstract: Disclosed herein are system, method, and computer program product embodiments for allowing completion of cardless transactions at a kiosk using an encoded identifier for that kiosk. A user of a mobile app may begin a transaction on their mobile device and, upon reaching a stage of the transaction where kiosk access is needed, receive instructions to visit a kiosk and scan the encoded identifier displayed by the kiosk. The scanned encoded identifier may be associated with the transaction, and the mobile app may transmit a request to complete the transaction at the kiosk.

Abstract: A computer-implemented method includes receiving a plurality of messages in a thread associated with a topic, providing the plurality of messages to a machine learning model configured to classify messages based on groupings, identifying, by the machine learning model, a first grouping associated with a first subset of the plurality of messages in the thread, wherein the first grouping is identified based on the first subset of the plurality of messages deviating from the topic, initiating a new thread comprising the first subset of the plurality of messages, determining a first user group comprising a first plurality of users associated with the first subset of the plurality of messages and granting the first user group access to the first thread.

Abstract: In some implementations, a device may receive report data associated with one or more reports generated by a source mainframe, wherein the report data is in a plain text data format. The device may convert the report data from the plain text data format to a platform-independent data format associated with metadata defining one or more attributes for the report data. The device may receive, from a client device, a query that includes one or more search parameters matching the one or more attributes for the report data. The device may provide the report data associated with the one or more attributes matching the one or more search parameters to the client device.

Abstract: A transaction card includes a near-field communication (NFC) component, a security component, a wireless component, one or more memories, and one or more processors communicatively coupled to the one or more memories. The device receives a signal from a user device attempting to access a secure application, and energizes the NFC component based on the signal received from the user device. The device causes the security component to generate an encrypted code based on the NFC component being energized, and provides, via the security component, the encrypted code to the wireless component. The device provides, via the wireless component, the encrypted code to the user device to permit the user device to utilize the encrypted code as authentication for accessing the secure application.

Abstract: A transaction device may include a power reception component configured to receive power from an external device with which the transaction device is to interact to perform a transaction. The transaction device may include a secure element configured to perform the transaction using the power received from the external device. The transaction device may include one or more peripheral components configured to perform one or more operations other than the transaction. The transaction device may include a power management component configured to determine at least one operation, of the one or more operations, to be performed in association with the transaction, and to route power received from the external device to at least one peripheral component, of the one or more peripheral components, capable of performing the at least one operation.