Abstract: A system and method are disclosed that leverage multi-factor authentication features of a service provider and intelligent call routing to increase security and efficiency at a customer call center. Pre-authentication of customer support requests reduces the potential for misappropriation of sensitive customer data during call handling. A contactless card uniquely associated with a client may provide a second factor of authentication to reduce the potential for malicious third-party impersonation of the client. Pre-authorized customer support calls are intelligently and efficiently routed in a manner that reduces the opportunity for malicious call interference and information theft.

Abstract: Methods and systems are described herein for outlier detection. The system may apply a single-tier including a minority expert model only or a two-tier machine learning model, including a majority expert model and a minority expert model. The system may generate the minority expert model by training an unsupervised machine learning model on oversampled training data, including synthetic sample outlier events. In some embodiments, the minority expert model may provide a binary result indicating an event belongs to an outlier category or not. In some embodiments, the minority expert model may include multiple component models providing a multi-class result indicating whether an event belongs to a sub-category of the outlier category. In application, the system may perform the outlier detection on events that are sequence-based or not.

Abstract: Systems and methods for analyzing data streams. In some aspects, the system receives a data stream including events associated with a plurality of users assigned to a token. The system processes the data stream to extract a first substream including events associated with a first user and a second substream including events associated with a second user. The system generates a first profile for the first user and a second profile for the second user. The system processes the first profile to determine that the first profile is associated with a cluster of profiles. The system processes the first substream to determine that the first substream includes events associated with the cluster of profiles and is above a threshold related to the cluster of profiles to trigger a notification to a first user device associated with the first user.

Abstract: A method, a system, and a computer program product for randomly generating and updating passwords for authentication to digital services. A first password associated with authenticating of a user is received. A plurality of random second passwords is generated based on the received first password. One or more random second passwords in the plurality of random second passwords are configured to authenticate the user for accessing at least one secure service. At least one random second password in the plurality of random second passwords is selected based on at least one factor and updated to generate an updated at least one random second password. The user is authenticated using the updated random second password for accessing the secure service.

Abstract: Methods and systems are described herein for outlier detection. The system may apply a single-tier including a minority expert model only or a two-tier machine learning model, including a majority expert model and a minority expert model. The system may generate the minority expert model by training an unsupervised machine learning model on oversampled training data, including synthetic sample outlier events. In some embodiments, the minority expert model may provide a binary result indicating an event belongs to an outlier category or not. In some embodiments, the minority expert model may include multiple component models providing a multi-class result indicating whether an event belongs to a sub-category of the outlier category. In application, the system may perform the outlier detection on events that are sequence-based or not.

Abstract: Techniques are disclosed for customizing the feedback provided to a user at a point-of-sale (POS) terminal upon completion of an electronic payment transaction. The feedback may include the content of one or more media files that may be customized by a user in response to different conditions being met, and which may be specified as part of a user profile. Additional or alternative feedback may be specified by an entity identified with the user's payment account, such as a bank or creditor, which may comprise additional or alternative media file(s) that may be identified in response to specific predetermined conditions being met upon the electronic payment transaction being initiated. The feedback may be sent to the POS terminal and/or to a different device based upon the type of electronic payment transaction and/or the capabilities of the POS terminal.

Abstract: Methods and systems are disclosed herein for secure communication between computing devices. A mobile device may communicate with an untrusted device to cause the untrusted device to send information (e.g., encrypted information that the untrusted device is unable to decrypt) to a server using an Internet connection of the untrusted device. The mobile device may have limited or no access to the Internet. To prevent potential security risks associated with using a public or untrusted device, the mobile device may encrypt information stored on the mobile device (e.g., stored in a mobile application associated with the server), send it to the untrusted device (e.g., by displaying a QR code to a camera of the untrusted device), and the untrusted device may send the information to the server via a network connection of the untrusted device.

Abstract: Methods and systems are described herein for generating dynamic conversational responses. For example, dynamic conversational responses may facilitate an interactive exchange with users. Therefore, the methods and systems used specialized methods to enriched data that may be indicative of a user's intent prior to processing that data through the machine learning model, as well as a specialized architecture for the machine learning models that take advantage of the user interface format.

Abstract: Methods and systems described herein may retrieve a data lineage associated with a first computing system comprising a plurality of services and data elements. The data lineage may indicate a plurality of interrelationships between the plurality of services and data elements. Based on the data lineage, a visualization of the first computing system may be generated. Based on the one or more interrelationships between a first data element and the plurality of services and data elements, one or more services and data elements affected by the change to the first data element may be identified. Based on the one or more services and data elements affected by the change to the first data element, the visualization of the first computing system to indicate the impact to the first computing system.

Abstract: A method of recovering blockchain wallet items, the method including: configuring a first smart contract to authorize a second smart contract to initiate transfer of one or more wallet items registered to the first smart contract to a location specified by the second smart contract; configuring the second smart contract to initiate transfer of the one or more wallet items from the first smart contract in response to receiving a first recovery verifier; receiving, via an API and by the second smart contract, a wallet recovery request associated with the first smart contract, the wallet recovery request specifying a third smart contract as being a recipient wallet; and based on the wallet recovery request and responsive to receiving the first recovery verifier, initiating, by the second smart contract, a transfer of the one or more wallet items from the first smart contract to the third smart contracts.

Abstract: Methods, systems, and apparatuses are described herein for improving the accuracy of authentication questions using e-mail processing. A request for access to an account may be received from a user device. A plurality of organizations may be identified. One or more e-mail associated with the account may be identified. The e-mails may be processed to identify one or more organizations that correspond to transactions conducted by a user. A modified plurality of organizations may be generated by removing, from the plurality of organizations, the one or more organizations. An authentication question may be generated and provided to the user device. A response to the authentication question may be received, and the user device may be provided access based on the response.

Abstract: Disclosed is a contactless card, and a system in which the contactless card may be used. The contactless card may include a chip component, a communication interface, processing circuitry, and electromagnetic field sensing circuitry. The electromagnetic field sensing circuitry of the contactless card may be operable to provide orientation signals to the processing circuitry when the contactless card is in proximity to an oscillating electromagnetic field output by a card reader device. The processing circuitry of the contactless card may be operable to receive the orientation signals. An orientation of the contactless card with respect to the mobile device may be determined. An orientation indication signal may be generated based on the determined orientation, and a haptic indication, an audio indication, a visual indication or a combination directing movement of the contactless card in a particular direction may be output.

Abstract: Methods and systems are described herein for an improved mechanism for authenticating users. In particular, the methods and systems facilitate variable authentication of users on mobile devices based on current and historical physical movement of the mobile devices at geographic locations and during predetermined time intervals while maintaining user privacy. Specifically, methods and systems authenticate users by comparing current motion data to historical motion data to determine if a user must be re-authenticated. For example, current motion data may be inconsistent with historical motion data and may cause re-authentication of a user. As another example, current motion data may be consistent with historical motion data and may not require re-authentication of a user. Moreover, the methods and systems alleviate privacy concerns by not transmitting sensitive data over one or more wired or wireless networks.

Abstract: Systems and methods of the present disclosure enable context-aware haptic error notifications. The systems and methods include a processor to receive input segments into a software application from a character input component and determine a destination. A context identification model predicts a context classification of the input segments based at least in part on the software application and the destination. Potential errors are determined in the input segments based on the context classification. An error characterization machine learning model determines an error type classification and an error severity score associated with each potential error and a haptic feedback pattern is determined for each potential error based on the error type classification and the error severity score of each potential error of the one or more potential errors. And a haptic event latency is determined based on the error type classification and the error severity score of each potential error.

Abstract: Aspects described herein may relate to a transaction exchange platform using a streaming data platform (SDP) and microservices to process transactions according to review and approval workflows. The transaction exchange platform may receive transactions from origination sources, which may be added to the SDP as transaction objects. As the transactions are received, the transactions may be analyzed to detect duplicate transactions and/or errors in the transactions. The transaction exchange platform may take steps to remediate transactions that are recognized as duplicates or predicted to generate one or more errors. Similarly, the transaction exchange platform may take steps to remediate transactions that are rejected by a clearinghouse.

Abstract: Disclosed are an apparatus, a system and a non-transitory computer readable medium that implement processing circuitry that receives non-dialog information from a smart device and determines a data type of data in the received non-dialog information. Based on the determined data type, the processing circuitry transforms the received first data using an input from a machine learning algorithm into transformed data. The transformed data is standardized data that is palatable for machine learning algorithms such as those used implemented as chatbots. The standardized transformed data is useful for training multiple different chatbot systems and enables the typically underutilized non-dialog information to be used to as training input to improve context and conversation flow between a chatbot and a user.

Abstract: Aspects described herein may relate to a transaction exchange platform using a streaming data platform (SDP) and microservices to process transactions according to review and approval workflows. The transaction exchange platform may receive transactions from origination sources, which may be added to the SDP as transaction objects. Microservices on the transaction exchange platform may interact with the transaction objects based on configured workflows associated with the transactions. Processing on the transaction exchange platform may facilitate clearing and settlement of transactions. Some aspects may provide for pausing the processing of transactions during a workflow. Other aspects may provide for a messaging microservice that permits communications between the transaction exchange platform and external third-parties.

Abstract: Aspects described herein may relate to a transaction exchange platform using a streaming data platform (SDP) and microservices to process transactions according to review and approval workflows. The transaction exchange platform may receive transactions from origination sources, which may be added to the SDP as transaction objects. As the transactions are received, the transactions may be analyzed to detect duplicate transactions and/or errors in the transactions. The transaction exchange platform may take steps to remediate transactions that are recognized as duplicates or predicted to generate one or more errors. Similarly, the transaction exchange platform may take steps to remediate transactions that are rejected by a clearinghouse.

Abstract: A user profile scoring platform may analyze a transaction log of a transaction account of a user to determine, based on transactions of the transaction log, a qualification status of the user, wherein the qualification status indicates that a characteristic of the user satisfies a threshold qualification metric. The user profile scoring platform may determine, based on the qualification status, a transaction-based score associated with the user, wherein the transaction-based score is determined using a transaction log analysis model. The user profile scoring platform may obtain, based on receiving the access information, a user score associated with a user transaction history that is associated with a plurality of transaction accounts that are associated with the user and different from the transaction account. The user profile scoring platform may perform an action based on the transaction-based score and the user score.

Abstract: Systems and methods are provided for on-demand delivery of a payload by an unmanned vehicle. An unmanned vehicle may comprise a chamber configured to house a payload and adjust a payload state. The payload state may be adjusted based on detection of a tampering event. An unmanned vehicle may also comprise an authentication system configured to allow access to the payload.