Abstract: Disclosed herein are system, method, and computer program product embodiments for a text-to-speech system. An embodiment operates by identifying a document including text, wherein the text includes both a structured portion of text, and an unstructured portion of text. Both the structured portion and unstructured portions of the text are identified within the document rich data, wherein the structured portion corresponds to a rich data portion that includes both a descriptor and content, and wherein an unstructured portion of the text includes alphanumeric text. A request to audibly output the document including the rich data portion is received from a user profile. A summary of the rich data portion is generated at level of detail corresponding to the user profile. The audible version of the document including both the alphanumeric text of the unstructured portion of the document and the generated summary is audibly output.

Abstract: A system includes one or more memory devices storing instructions, and one or more processors configured to execute the instructions to perform steps of a method for providing customer data access during a migration process. The system may initiate a transfer of customer data from a source data server to a system platform and transfer a subset of the customer data to a temporary data storage. The system may modify the temporary copy of customer data and generate an instruction to modify the permanent copy of customer data. In response to the completion of the transfer of customer data from the source data server to the system mainframe, the system may then transfer and execute the instruction to modify the permanent copy of customer data.

Abstract: A system and method are disclosed in which cash deposits may be made at merchant locations who support such deposits. Using a mobile phone or other hand-held device, a bank customer requests a cash deposit from a banking app, receives a barcode on the mobile device, the barcode containing embedded information indicating the cash deposit amount, and presents the barcode to the merchant, along with the cash to be deposited. Once the transaction with the merchant is complete, the account of the bank customer's account is credited with the cash amount. The bank uses behavioral and historical data of the bank customer to customize a cash deposit limit for the customer.

Abstract: Various embodiments are directed to techniques for ensuring that a negotiable instrument has not been altered between the time the instrument leaves the hands of the payor and when the check is presented for redemption by the payee by recording an image of the check in a data block in a blockchain and retrieving the image when the check is presented for redemption for comparison with the check. A match between the stored image and the check indicates that no alteration of the check has occurred.

Abstract: A wearable transaction device may include a housing, a fastener component attached to the housing, and an electronic chip secured within the housing. The wearable transaction device may detect a connection with a user device, and receive, from the user device and via the connection, security information for operating the wearable transaction device. The security information may indicate one or more conditions for placing the wearable transaction device in a payment mode or a non-payment mode. The wearable transaction device may receive a request to perform the transaction, and determine, based on the security information, whether the wearable transaction device is in the payment mode or the non-payment mode. The wearable transaction device may selectively perform the transaction based on whether the wearable transaction device is in the payment mode or the non-payment mode.

Abstract: A device may initiate an automated script to perform one or more interactions with a browser application and identify a first element in a page rendered by the browser application that satisfies one or more accessibility criteria, wherein the first element may include text that is readable by a screen reader application and/or an attribute that causes the first element to be navigable using a keyboard. The device may modify the first element to be inaccessible to the screen reader application and the keyboard and insert, into the page, a second element including text that is readable by the screen reader application to describe the one or more interactions that the automated script is performing. The client device may restore the page to an original state based on determining that the automated script has finished executing.

Abstract: Disclosed herein are system, method, and computer program product embodiments for categorizing customer complaints on social media using a model trained on customer voice calls or chats with agents. Additionally, users interested in monitoring regulatory compliance issues based on customer complaints can receive notifications regarding complaints that are linked to regulatory topic areas, without the need to manually scan vast numbers of social media postings.

Abstract: The packet capture manager uses a multi-tiered storage for storing captured network traffic. Captured packets are stored on a primary storage with a time-to-live according to a retention policy. The packet capture manager receives instructions from one or more network monitoring devices identifying one or more captured packets as packets of interest. The packet capture manager flags the identified packets as packets of interest, moves the flagged packets to a secondary storage, and changes the TTL of the moved packets. A machine learning model analyzes historical data of the instructions received from the one or more network monitoring devices. The packet capture manager uses the machine learning model to identify packets of interest and move identified packets to the secondary storage without specific instructions from a network monitoring device.

Abstract: Systems and methods are disclosed for determining one or more credit lines based on statistical approximations of credit line optimization models. By approximating the results of the optimization model, the disclosed embodiments may provide real-time account level credit line determinations based on fewer criteria than used in the optimization models. Other aspects of the disclosed embodiments are described herein.

Abstract: Disclosed herein are system, method, and computer program product embodiments for process corruption prevention. An embodiment operates by determining security vulnerabilities for an entity and correlation values for the security vulnerabilities by applying completed processed records of the entity to a machine learning model. Each of the correlation values quantifies a relationship strength between a security vulnerability and fraudulent activity. The embodiment further operates by generating a security vulnerability score for the entity using the correlation values and identifying one or more patches for at least one of the security vulnerabilities. The one or more patches may be ranked and the ranking may be revised using a feedback mechanism after the one or more patches are implemented by the entity.

Abstract: In certain embodiments, a presentation of a user interface may be dynamically modified for a user based on data related to the user's email address or other user identifier. As an example, the user interface may be caused to reflect the look and feel of an interface of an entity trusted by the user, incorporate data items related to the user's identifier, or effectuate other modifications. In some embodiments, a user identifier of a user may be received via a user interface associated with the third party, and a query for data related to one or more user accounts associated with the user identifier may be generated. Based on the query, multiple datasets associated with different user accounts may be received, and a first dataset associated with a first account of the user may be selected over other datasets associated with the user's other accounts effectuate the presentation modification.

Abstract: A synthetic identity network for detecting synthetic identities may receive a first request for credit including one or more user attributes, compare the one or more user attributes to one or more stored user identities, create a new user identity, flag the new user identity as a potentially synthetic identity based on comparing the one or more user attributes to the one or more stored user identities, receive a second request for credit including or more second user attributes, compare the one or more second user attributes to the one or more user attributes associated with the potentially synthetic identity, prepare a notice including the potentially synthetic identity and a credit request identifier, and transmit the notice to one or more servers.

Abstract: A scalable system and method for completing a model task using a serverless architecture is disclosed. The system may include memory storing instructions and one or more processors. The method may include receiving a request to complete a model task; retrieving a first model and a first hyperparameter based on the request; provisioning computing resources to a first development instance configured to train the first model based on the first hyperparameter and the model task; training, by the first development instance, an instance of the first model to produce a trained model and terminating said training upon satisfaction of a training criterion; receiving the trained model and a first performance metric; receiving a second performance metric associated with a second model; and terminating the development instance based on a determination that the termination condition is satisfied based on at least one of the first and second performance metrics.

Abstract: A computer-implemented method for operating an interactive customer service system may include: receiving interaction information of a plurality of customer communications that were each serviced by a respective interaction unassociated with a predetermined interaction model; and in response to determining, based on the received information, that a threshold number of the communications have a common root cause: generating a further interaction model of a further interaction, based on interaction information of the customer communications having the common root cause, by employing a machine learning model trained, based on (1) sets of previous interaction information with respective common root causes as training data and (2) respective interactions corresponding to the respective common root causes as ground truth, to generate an output interaction model for a given set of interaction information of customer communications having a given common root cause; and configuring the interactive customer service sys

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: Systems and methods are disclosed for managing workload among server clusters is disclosed. According to certain embodiments, the system may include a memory storing instructions and a processor. The processor may be configured to execute the instructions to determine historical behaviors of the server clusters in processing a workload. The processor may also be configured to execute the instructions to construct cost models for the server clusters based at least in part on the historical behaviors. The cost model is configured to predict a processor utilization demand of a workload. The processor may further be configured to execute the instructions to receive a workload and determine efficiencies of processing the workload by the server clusters based at least in part on at least one of the cost models or an execution plan of the workload.

Abstract: The disclosed embodiments include methods, systems, and articles of manufacture for enabling beta testing of new features within a native application. In one embodiment, a native application executed by a client device may include executable instructions that are activated and executed only upon indication of a user belonging to a beta test group. The client device may receive a signal from a service or content provider that includes test group information indicating whether a user is a member of a test group. The client device may process the received signal to determine whether the user is a member of a test group and, if so, activates and executes certain instructions received as part of the native application that define a user interface enabling access to additional functionality unavailable to a user determined not to be a member of a test group.

Abstract: The disclosed technology includes a distributed ledger system that can include one or more transaction blocks that are associated with one or more transaction records of an account corresponding to the primary account number. The system may allocate a first type block in a first distributed ledger, and the first type block may be utilized to identify a classification type associated with the first primary account number. The system may receive, at the first node, a first transaction indication associated with the first primary account number. Responsive to receiving the first transaction indication, the system may bind a first transaction block to the first distributed ledger. Transaction blocks may be configured for selective control and/or selective replicated to other nodes of the system. In response to an end-of-cycle indication, the first transaction block may be locked to prevent further modification.

Abstract: A device receives delivery information indicating instructions for delivery of an item at a location, wherein the delivery information include an image of the location with a designated point for delivering the item. The device receives information indicating that a user device, associated with a delivery person, is at the location, and processes the delivery information and the information indicating that the user device, associated with the delivery person, is at the location, with a machine learning model, to generate delivery instructions for the item, wherein the delivery instructions include augmented reality information indicating the designated point for delivering the item at the location. The device provides the delivery instructions to the user device, wherein the delivery instructions enable the user device to utilize the augmented reality information to display the designated point for delivering the item within a live image of the location.

Abstract: Systems and methods disclosed herein securely provide confidential information associated with a user during an active voice call conducted using the user's mobile device. The confidential information may be provided by generating the information in spoken form and inserting the spoken information into an audio stream of the voice call. For example, a customer may be on a phone call with a customer agent. The customer agent may ask the customer for a credit card number in order to process a financial transaction. The customer may select the credit card number via an application executing on the customer's mobile phone. The application may cause the credit card number to be spoken out loud during the voice call. A voice sample of the spoken credit card number in inserted into the audio stream of the voice call and is therefore, audible to the customer and the customer agent without being overheard by a third party.