Abstract: Disclosed is a computer-implemented method that includes: receiving, from a user device, a search query comprising item data; obtaining, from at least one database, a user-specific embedding vector; modifying, based on the search query received from the user device, the user-specific embedding vector to generate an updated user-specific embedding vector; obtaining, from the at least one database, one or more item-specific embedding vectors based on the updated user-specific embedding vector, wherein the one or more item-specific embedding vectors are associated with one or more items; and causing an interface of the user device to display the one or more items associated with the one or more item-specific embedding vectors.

Abstract: Embodiments described herein reduce resource insufficiency of a resource source despite inconsistent resource accumulation at the resource source. For example, a request frequency may be determined to define times at which the resource source is predicted to be sufficient despite the inconsistent accumulation or influx. In one use case, with respect to a distributed computing environment having computing resource source(s)/pool(s), a requesting system may identify a machine learning model trained to generate predictions for a resource source at which inconsistent resource accumulation occurs. The system may obtain accumulation data that describes accumulation events at which resources were made available at the resource source.

Abstract: Methods and systems are described herein for applying padding (e.g., a scale factor) to a detected object (e.g., a rotated rectangle or other shape) in an image before rotation correction is applied. By applying the padding prior to the rotation correction, the system is more efficient as rotation correction may be performed simultaneously with other processing tasks such as cropping and downscaling. For example, by applying padding first, the system is able to keep rotation correction, cropping, and/or downscaling as a single step, which is quicker and more efficient.

Abstract: Systems and methods for improving component access for cloud service users. The systems and methods allow for users to access additional cloud components through data layer operations such as routing table updates. Notably, the data layer may be modified by the cloud service users themselves and thus avoid restriction in inactivity by the cloud service provider.

Abstract: Embodiments disclosed herein provide techniques for secure PIN management for contactless cards using an application on a computing device such as a mobile computing device. In some embodiments, the computing device may have an application installed enabling the computing device to act as a secure endpoint that enables communication between the contactless card and a backend server to facilitate PIN management. For example, the application may enable a mobile device to be utilized to view and/or change the PIN associated with a contactless card that is brought in proximity of the mobile device.

Abstract: Systems and methods for predicting network outages based on detected network-wide resilience. For example, the system may receive first computer network traffic data for a first time period and a second time period, wherein the first computer network traffic data for the first time period indicates a first load on a first computer network. The system may determine a first error resilience metric based on the first load. The system may determine a first error resilience rate-of-change for the first computer network based on the first error resilience metric. The system may determine a first likelihood of a first network outage based on comparing the first error resilience rate-of-change to the threshold error resilience metric.

Abstract: A system receive data from a web server and via one or more application programming interface (API) endpoints. The data includes one or more indications of one interacting with one or more variants. The system allocates network traffic to the variant based on the variant overperforming in relation to one or more other variants.

Abstract: Methods and systems are described herein for facilitating segmentation of training data using measures of statistical dispersion (e.g., Gini impurities) of dataset features. The system determines, from a training dataset, a target feature and candidate features. The system determines, for the target feature in relation to each candidate feature, first Gini impurities. The system selects a first and second feature having the lowest first Gini impurities. The system determines, for the target feature in relation to a first combination of the first and second features, a second Gini impurity. If the second Gini impurity does not satisfy a threshold, the system selects a third feature having the next lowest first Gini impurity and determines a third Gini impurity for a second combination of the first, second, and third features. If the third Gini impurity satisfies the threshold, the system trains a model using the target, first, second, and third features.

Abstract: Systems as described herein may implement a mechanism for dynamic identity proofing. A dynamic identity proofing system may receive first user input information and browser information from a user device conducting a transaction with an interaction entity. The system may determine a risk score indicating a likelihood the transaction is fraudulent. Based on the risk score exceeding a threshold value, the system may use a machine learning model to determine confirmative information to lower the risk score. The system may cause display of one or more web elements on the checkout page prompting for the confirmative information. The system may determine an updated risk score based on second user input information responsive to the confirmative information. Accordingly, if the updated risk score does not exceed the threshold value, the system may cause the checkout page to be automatically populated with additional secure information.

Abstract: In some implementations, a device may obtain an indication of one or more permissions associated with a dataset shared by a data provider via a first execution environment. The device may obtain an indication of one or more data processing applications associated with respective intents, wherein the one or more data processing applications are executable via a second execution environment, and wherein the respective intents indicate an intended use of data in association with the one or more data processing applications. The device may detect a data usage violation associated with a data processing application, from the one or more data processing applications, that has accessed and processed data from the dataset in the second execution environment, based on an intent associated with the data processing application not being permitted by the one or more permissions. The device may perform an action based on detecting the data usage violation.

Abstract: In some implementations, a device may train the model to generate embeddings for log files associated with an application, and to enable the model to generate embeddings for sensitive information included in a set of training log files. The device may receive a log file associated with the application. The device may generate a compressed log file including a set of embedding vectors associated with records included in the log file, where a record that includes sensitive information is associated with one or more embedding vectors for the sensitive information and one or more embedding vectors for other information included in the record. The device may store the compressed log file including the set of embedding vectors where a size of the compressed file is less than a size of the log file, and the embedding vectors obfuscate the records included in the log file.

Abstract: Disclosed are techniques and apparatuses that are configured to receive an indication that a web browsing session executing on an enterprise server needs additional information based on a request for additional information being sent to a client device. The request may include an identifier of the web browsing session and an identifier of an enterprise server that initiated the web browsing session. A globally unique identifier related to the web browsing session and an identifier of the enterprise server is stored in a common data store. The web browsing session may be paused when the web browsing session requests additional information from a client device. The client device may respond with the additional information. The system may provide the identifier of the enterprise server to a load balancing component so the identified web browsing session executing on the enterprise server may continue to be used.

Abstract: Methods and systems are described herein for preventing unauthorized data access based on an analysis of time series data. For example, a request to authorize a candidate event may be received. The request can indicate sequential event data representing a sequence of events to be retrieved. Discretized event data can be generated by assigning an encoding to each event indicating an assigned temporal bucket. The discretized event data can be input to an ensemble model, including one or more trained artificial intelligence models, to (i) generate natural language text representing the sequence, including additional context indicating semantic and contextual information associated with the events, (ii) generate an embedding representing the natural language text, (iii) determining an authorization score based on the embedding, and (iv) determining a classification result for the candidate event based on the authorization score.

Abstract: In some implementations, a system may obtain, from a first data repository, a first dataset that includes event data associated with a generic schema. The system may infer an event-specific schema that defines an organizational structure for the event data based on common attributes identified among a plurality of events included in the event data using one or more data analytics functions. The system may store, in a second data repository, a second dataset in which the event data is partitioned based on the organizational structure defined by the event-specific schema. The system may generate a third dataset that includes a subset of the event data included in the second dataset that satisfies one or more registration parameters related to an extract, transform, load (ETL) use case. The system may provide the third dataset to an ETL system configured to process the third dataset based on the ETL use case.

Abstract: Systems and methods for generating synthetic video are disclosed. For example, a system may include a memory unit and a processor configured to execute the instructions to perform operations. The operations may include receiving video data, normalizing image frames, generating difference images, and generating an image sequence generator model. The operations may include training an autoencoder model using difference images, the autoencoder comprising an encoder model and a decoder model. The operations may include identifying a seed image frame and generating a seed difference image from the seed image frame. The operations may include generating, by the image sequence generator model, synthetic difference images based on the seed difference image. In some aspects, the operations may include using the decoder model to synthetic normalized image frames from the synthetic difference images. The operations may include generating synthetic video by adding background to the synthetic normalized image frames.

Abstract: Example embodiments of systems and methods for data transmission system between transmitting and receiving devices for use in a tap and walk store are provided. In an example embodiment, the transmitting device can generate a diversified key using the master key, protect a counter value and encrypt data prior to transmitting to the receiving device, which can generate the diversified key based on the master key and can decrypt the data and validate the protected counter value using the diversified key. Disclosed systems allow a user to purchase items utilizing the disclosed transmitting device.

Abstract: Methods and systems for sensor-based provisioning for one or more users of a vehicle are described herein. In some aspects, the system may determine a first user of the vehicle and execute sensor functions to store first information associated with the vehicle. The system may determine a second user and execute the sensor functions to store second information associated with the vehicle. The system may retrieve total resource usage associated with the vehicle. The system may determine a fractional variable for the first user and a fractional variable for the second user. This allows the system to assign a first portion of the total resource usage to the first user based on the first fractional variable and a second portion of the total resource usage to the second user based on the second fractional variable.

Abstract: In some implementations, a system may host an application that includes a host container and multiple micro frontend (MFE) components that each include an interface associated with the application. The system may receive, at the host container and from a client device, a request to initiate the application. The system may identify a set of attributes associated with a user that provided the request to initiate the application. The system may determine a flow associated with the application based on the set of attributes associated with a user that provided the request to initiate the application, wherein the flow associated with the application includes a sequence in which a subset of the multiple MFE components is presented to the user. The system may present, to the client device, the subset of the multiple MFE components in accordance with the flow based on the set of attributes associated with the user.

Abstract: Systems and methods for triggering a virtual certification number (VCN) generation for use at a source include receiving a VCN generation request from an external entity, the VCN generation request comprising an external request code, external risk signals, and one or more source data for the source, verifying a registration authentication of an account associated with the external request code by comparing the external request code to a database entry, identifying a certification mechanism reference identifier associated with the external request code based on verifying the registration authentication, generating a risk authentication based on a risk analysis conducted using the external risk signals and the external request code, identifying a source identifier based on the one or more source data, and generating the VCN based on the certification mechanism reference identifier and the source identifier.

Abstract: A conference system is described that associates a first device and a second device to the same user, compares a first input from the first device and a second input from the second device, and modifies a setting of a conference session. The first input and the second input may be a video input or an audio input. The modification may include, for example, noise removal, determination of the user's AV feed device, or removing a background image.