Abstract: Systems and methods for securely pairing a transmitting device with a receiving device are described. The systems and methods may communicate with a first device via a first communication method over a wireless communication network. The systems and methods may transmit, to the first device via a second communication method, a first sensory pattern representing a first key. In addition, the system and methods may communicate with the first device via the first communication method using the first key.

Abstract: Systems, methods, and computer-readable media for communications between applications in a mobile operating system. A first application may receive a request for data from a second application. The first application may generate a first URL to the second application, a parameter of the first URL comprising an identifier of the first application. A mobile operating system may access the first URL to open the second application. The second application may validate credentials for an account and initiate a server on a port. The second application may generate a second URL to the first application, a parameter of the second URL comprising the port. The operating system may access the second URL to open the first application. The first application may establish a connection with the server using the port specified in the second URL and receive data from the second application via the connection with the server.

Abstract: An apparatus includes a display, a memory, a light sensor array and a light source array. The light source array emits light to display an image on the display. A controller is configured to receive a sensor output from each light sensor in the light sensor array. An ambient-light illuminance difference between a first illuminance of a first ambient light externally directed onto a first region of the displayed image of the display and a second illuminance of a second ambient light externally directed respectively onto a second region of the displayed image of the display is computed. Light source controls of light sources of the light source array are varied to change a luminous emittance of the light source array within the at least one second region of the displayed image so as to reduce a luminance difference between the first region and the second region of the displayed image.

Abstract: Systems and methods of the present disclosure enable IoT-based social networking to detect, using IoT devices at a location, device signals associated with a first user device of a first user. A first user profile associated with the first user device is determined in response to the device signals. User attributes stored in the first user profile are accessed and extracted. A trained profile similarity model is used to determine similarity measures between the first user profile and other user profiles based on the user attributes. At least one similar user profile to the first user profile is identified based on the similarity measures. A meet-up point occupancy of each meet-up point at the location is determined based on a record of meet-up points to identify an open meet-up point. A meet-up recommendation is generated indicating the open meet-up point and the other user profiles.

Abstract: Embodiments include techniques to receive and process data from a data service provider, communicate a plurality of messages comprising the data to a streaming data platform and detect a failure of delivery of the plurality of messages to the streaming data platform. Embodiments further include techniques communicate the plurality of messages to a distributed message queue service of a distributed message queue system, publish each of the plurality of messages to the streaming data platform, determine each of the plurality of messages published to the streaming data platform was successful or unsuccessful, and retry publication of each unsuccessfully published message of plurality of messages to the streaming data platform.

Abstract: Systems and methods for integrating application components in a web application are disclosed. The method includes: executing the web application, the web application configured to display a web page element; receiving, by a library component of the web application, a request from the web application to retrieve a list of one or more application component definitions loadable by the web application; retrieving, by the library component, the list of one or more application component definitions from a manifest; receiving a request to load an application component of the one or more application components; binding, by the library component, attributes and events for each of the one or more application components from the web application; appending the application component into the web page element; and rendering the application component and the web page element using the web browser so that the application component is displayed in the web browser.

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 via a backchannel to reduce the potential for malicious third-party impersonation of the client prior to transfer of the call to the customer call center. Pre-authorized customer support calls may be intelligently and efficiently routed directly to call center agents, without incurring further delay. During call handling, call center agents may initiate further client authentication processes, including contactless card authentication requests, over one or more different communication channels for authorizing access to sensitive information or to allay suspicion.

Abstract: In some implementations, a device may provide, for display via a display screen, a graphical user interface (GUI) that includes a first page and one or more sheets corresponding to respective secondary pages, wherein the one or more sheets include respective sets of one or more display elements from respective sets of display elements associated with the respective secondary pages. The device may detect a first gestural interaction in an area of the display screen that is associated with a portion of the GUI, the first gestural interaction indicating an action. The device may update, based on detecting the first gestural interaction and the action, the GUI to cause one or more other portions, from the first page and the one or more sheets, of the GUI to display updated information in accordance with the action. The device may provide, for display, the GUI indicating the updated information.

Abstract: Aspects described herein may relate to techniques for detecting login activity to a financial account during a knowledge-based authentication process. The login activity may be related to access to an online interface for the financial account. The detection of login activity during the authentication process my indicate that the integrity of the authentication process is compromised as login access may provide an individual with transaction data that may be used to answer transaction-based authentication questions. As a result of detecting login activity, an alternative authentication process may be initiated or an authentication request related to the financial account may be denied.

Abstract: Provided are approaches for concealing or obscuring transaction card numbers. In some approaches, a transaction card may include a body comprising a first main side opposite a second main side, and a plurality of structures extending from at least one of the first or second main sides. In a bent configuration of the body, the plurality of structures separate from one another, in a substantially flat configuration of the body, adjacent structures of the plurality of structures abut one another.

Abstract: In some aspects, a computing system obtain a first dataset including a set of original data samples and a first set of spurious data samples. Based on a time period expiring, the computing system may replace the first set of spurious data samples in the first dataset with a second set of spurious data samples. The computing system may obtain an indication that a second dataset is available via a third-party computing device. Based on a determination that a subset of samples of the second dataset correspond to the first set of spurious data samples, the computing system may determine a time window in which an incident occurred. As an example, the time window may be determined to correspond to a time before the first set of spurious data samples were replaced with the second set of spurious data samples.

Abstract: In some aspects, a computing system may iterate between adding spurious data to the dataset and training a model on the dataset. If the model's performance has not dropped by more than a threshold amount, then additional spurious data may be added to the dataset until the desired amount of performance decrease has been achieved. the computing system may determine the amount of impact each feature has on a model's output. The computing system may generate a spurious data sample by modifying values of features that are more impactful than other features. The computing system may repeatedly modify the spurious data that is stored in a dataset. If a cybersecurity incident occurs (e.g., the dataset is stolen or leaked), the system may identify when the cybersecurity incident took place based on the spurious data that is stored in the dataset.

Abstract: In some aspects, a computing system may generate uninformative features that may be added to a dataset of real features to use as a baseline for determining the quality of an explanation of model output. The uninformative features may be features that do not correlate with what a model is tasked with predicting (e.g., the uninformative features may be random values), and the real features may be informative and correlate with what the model is tasked with predicting (e.g., variables of a dataset sample). A machine learning model may be trained on a dataset that includes both the real features and the uninformative features. The computing system may generate feature attributions for model output, which may include feature attributions for the uninformative features and the real features in the dataset.

Abstract: Systems and methods use dynamically generated validation rules. These validation rules comprise a first validation rule portion that is generated using a standardized validation process (e.g., corresponding to a standardized schema) and a second validation rule portion that is generated using a validation process selected based on a non-standardized schema that is specific to a respective asset type of the plurality of respective asset types.

Abstract: Provided, in an aspect, is a method for performing an online transaction using a graphical construct. The method can include receiving, by a client device, inputs to generate the graphical construct; transmitting to a server in communication with the client device, a request to generate the graphical construct; receiving, by the client device, the generated graphical construct and a summary information from the server; displaying, through a user interface of the client device, a summary screen including the generated graphical construct and the summary information; embedding, by the client device, the generated graphical construct on a third-party application running on the client device; sending, by the client device, a transaction request to perform the online transaction using the generated graphical construct; and presenting for display, through the user interface of the client device, a notification including a status of the online transaction.

Abstract: In some embodiments, an artificial intelligence system for communicating predicted hours of operation to a client device may be provided. In some embodiments, prediction models may be generated using a randomly selected subset of a training data set comprising: a group of transaction authorizations associated with a merchant group related to the merchant, and a ground truth data set for the merchant group identifying hours of operation of merchants of the merchant group. A request for hours of operations of a merchant may be received from a client device. A set of transaction authorizations associated with the merchant may be obtained, and the prediction models may be used to determine prediction indications for a plurality of time intervals based on the set of transaction authorizations. The prediction indications for the time intervals may be communicated to the client device.

Abstract: A computer-implemented method for using a machine-learning trained predictive engine to predict failures, comprising receiving, from a user using a graphical user interface, electronic transaction data comprising an item and candidate transaction terms, the candidate transaction terms comprising a first transaction term, the electronic transaction data being associated with a candidate transaction. The method may determine, by a machine learning predictive engine, a likelihood of success of the candidate transaction based on the electronic transaction data, and may determine, by the machine learning predictive engine, based on the first transaction term, a second transaction term that, together with the first transaction term, increases the likelihood of success of the candidate transaction above a predetermined threshold. An indication of the second transaction term and an indication of the likelihood of success of the candidate transaction may be displayed on the graphical user interface.

Abstract: In certain embodiments, intent prediction and dialogue generation may be facilitated. In some embodiments, a chat initiation request may be obtained from a user. The latest activity information associated with the user may be provided to a prediction model to obtain a first set of predicted intents of the user. For each intent of the first set of predicted intents, a candidate question may be selected from a question set based on the candidate question matching the intent. In some embodiments, the candidate questions may be simultaneously presented on the chat interface.

Abstract: In some aspects, a computing system may generate uninformative features that may be added to a dataset of real features to use as a baseline for determining the quality of an explanation of model output. The uninformative features may be features that do not correlate with what a model is tasked with predicting (e.g., the uninformative features may be random values), and the real features may be informative and correlate with what the model is tasked with predicting (e.g., variables of a dataset sample). A machine learning model may be trained on a dataset that includes both the real features and the uninformative features. The computing system may generate feature attributions for model output, which may include feature attributions for the uninformative features and the real features in the dataset.

Abstract: In some aspects, a computing system obtain a first dataset including a set of original data samples. The computing system may generate a key that indicates a location within the first dataset where spurious data should be stored. The computing system may determine a modified value associated with a first data sample of the set of original data samples, where the modified value causes a machine learning model to generate output that does not match a label associated with the first data sample. Based on the first data sample, the computer system may generate a spurious data sample comprising the modified value. Based on the key, the computer system may add the spurious data sample to the first dataset. In some aspects, based on a request for the first dataset, the computing system may remove the spurious data sample from the first dataset.