Abstract: A method implements input validation using mathematical expressions. The method includes receiving an input string, scanning the input string to locate a hit string matching a hit expression from a validation package, and converting the hit string to a list of values corresponding to characters from the hit string. The method further includes validating the hit string by evaluating a validation expression from the validation package using the list of values to generate a validation result and returning the validation result.

Abstract: Systems and methods that may be used to provide policies and protocols for blocking decryption capabilities in symmetric key encryption using a unique protocol in which key derivation may include injecting a random string into each key derivation. For example, a policy may be assigned to each client device indicating whether the client device has been assigned encryption only permission or full access permission to both encrypt and decrypt data. The disclosed protocol prevents client devices with encryption only permission from obtaining keys for decryption.

Abstract: An entry validation system executed by a processor, may compare an entry into a user interface (UI) field with at least one range of valid entries. The at least one range of valid entries may be generated by a machine learning (ML) system by clustering known valid data using a clustering algorithm producing a lowest number of clusters that absorbs all of the known valid data within the clusters. In response to the comparing, the entry validation system may provide a determination of validity or invalidity to an application displaying the UI field. The determination of validity may cause the entry to be processed by the application, and the determination of invalidity may cause the application to reject the entry.

Abstract: A method implements calibrated risk scoring and sampling. Features are extracted from a record. A risk score, associated with the record, is generated from the features using a machine learning model. The record is mapped to a risk bucket using the risk score. The risk bucket may include multiple risk bucket records. The record is selected from the risk bucket records with a sampling threshold corresponding to the risk bucket. A form prepopulated with values from the record is presented to a client device.

Abstract: Systems and methods for quantifying saved time during data entry.

Abstract: Aspects of the present disclosure provide techniques for application navigation recommendations using machine learning. Embodiments include determining one or more pages accessed by a user within an application. Embodiments include providing one or more inputs to a machine learning model based on the one or more pages accessed by the user. Embodiments include receiving, from the machine learning model based on the one or more inputs, one or more predicted pages. Embodiments include displaying, in a user interface, one or more elements recommending the one or more predicted pages to the user. Embodiments include receiving a selection of a given element of the one or more elements. Embodiments include navigating within the user interface, based on the selection, to a given page of the one or more predicted pages that corresponds to the given element.

Abstract: A processor may receive an image and determine a number of foreground pixels in the image. The processor may obtain a result of optical character recognition (OCR) processing performed on the image. The processor may identify at least one bounding box surrounding at least one portion of text in the result and overlay the at least one bounding box on the image to form a masked image. The processor may determine a number of foreground pixels in the masked image and a decrease in the number of foreground pixels in the masked image relative to the number of foreground pixels in the image. Based on the decrease, the processor may modify an aspect of the OCR processing for subsequent image processing.

Abstract: Systems and methods that implement a paired-consistency-based process for evaluating and or regulating fairness in machine learning models.

Abstract: Systems and methods that may be used to provide a predictive tax loan or other monetary advance before the loan recipient (e.g., a taxpayer) prepares and files its tax return. A risk of providing a predictive tax loan or monetary advance is modeled separately from a machine learning model used to determine the anticipated tax refund amount and tax loan. The disclosed systems and methods may also predict accurate tax withholdings based on multiple machine learning models from multiple services, including non-payroll related services.

Abstract: Knowledge about a user is used to determine whether one or more messages received by the user are malicious. The knowledge about the user may be based on the user's financial history such as transaction records. Particularly, a classifier model is trained on a supervised approach using a dataset containing, for example, a categorization of incoming messages (e.g., password change message), the user's aggregated transaction records, message attributes, user attributes, and corresponding classification labels. After the training, the classifier model is deployed to determine whether an incoming message is malicious.

Abstract: A processor may receive a call transcript including text and form a text string including at least a portion of the text. The processor may generate a situation description of the call transcript, which may comprise processing the text string using a transformer-based machine learning model. The processor may generate a trouble description of the call transcript, which may comprise creating a sentence embedding of the situation description, creating sentence embeddings for a plurality of utterances within the portion of the text, determining respective similarities between the sentence embedding of the situation description and each of the sentence embeddings for each respective one of the plurality of utterances, and selecting at least one of the plurality of utterances having at least one highest determined respective similarity as the trouble description. The processor may store a call summary comprising the situation description and the trouble description in a non-transitory memory.

Abstract: Systems and methods are provided for categorizing a transaction description using natural language processing.

Abstract: A method for using shareable and nested transactions on hash chains includes appending a data block of a transaction of a first hash chain to a second hash chain. The second hash chain originates from a tail block of the first hash chain. The method further includes removing the data block from the transaction by setting a tail block identifier of the second hash chain to a previous block appended to one of the first hash chain and the second hash chain prior to the data block. The method further includes updating the transaction with updated transaction data by setting the tail block identifier of the second hash chain to the updated data block. The method further includes appending the second hash chain to the first hash chain by setting the tail block of the first hash chain to the tail block of the second hash chain.

Abstract: A method for privacy preserving synthetic string generation using recurrent neural networks includes receiving input data that includes a plurality of strings with private information. A neural network model is trained using the plurality of strings. The neural network model includes a recurrent neural network (RNN). An anonymous string is generated with the neural network model after training the neural network model with the plurality of strings from the input data. The anonymous string is validated to preclude the private information from the anonymous string. Anonymous data is transmitted that includes the anonymous string and precludes the private information in response to a request for the anonymous data.

Abstract: Certain aspects of the present disclosure provide techniques for detecting data errors. A method generally includes receiving a new value as user input for a data field, generating histogram-based approximations of kernel density estimates generated based on valid data and invalid data associated with the data field, determining a likelihood that the new value is a valid value and a likelihood that the new value is an invalid value, computing a likelihood ratio test statistic based on a ratio of the likelihoods, and classifying the new value as valid or invalid based on comparing the likelihood ratio test statistic to a likelihood ratio test threshold.

Abstract: A method, computer program product, and system are provided. A request to initiate a virtual environment for a first user is received from a first application via a network connection with a first user device, a request. The first user is represented by a first avatar within the virtual environment. Based on the request, session data of the first application for the first user is identified. A second user is selected based on the session data. The second user is represented by a second avatar within the virtual environment. Via the network connection, a video is displayed to the first user, transforming a real-world image of the second user into the second avatar. The virtual environment is launched on the user device of the first user, and the first avatar and the second avatar are assigned to adjacent locations within the virtual environment.

Abstract: A method implements a dataset rank metric for measuring dataset relevance. Metadata is identified for a plurality of datasets. A graph structure is generated in storage. The graph structure includes a multitude of nodes connected by a multitude of edges. Each node of the multitude of nodes representing a respective dataset of a multitude of datasets, the multitude of edges connecting the multitude of nodes according to a data lineage determined from metadata of the multitude of datasets. A composite score is generated for each node of the graph. The computer processor iteratively processes the composite scores for the multitude of nodes of the graph to generate a dataset rank for each dataset. The multitude of datasets is presented in an interface, sorted according to the respective dataset rank of each dataset.

Abstract: A mobile device application for time tracking provides a dynamic display that auto-populates descriptions (e.g., a job description, a task description) for the hours to be entered. For instance, when a user clocks-in using the application, an auto-population engine executed by the mobile device analyzes the history of time entries by the user and generates a list of likely descriptions for the current entry. The list is displayed as selectable objects. When the user selects an object, the corresponding description is automatically added for the current time entry. The generated list may be based on information associated with the current time entry (e.g., time of day, location, etc.) and historical patterns of time entries. One or more machine learning models may be used to learn the historical patterns.

Abstract: A method includes processing a set of query texts to identify a set of expressions, where each expression references a set of columns of datetime data in a datastore. The method also includes training a statistical model to determine a distribution of the datetime data for each column that was identified. The method further includes processing the set of expressions to generate a directed graph including more than one nodes and a plurality of edges, where each node represents one of the columns or a transformation applied by one of the expressions to one of the columns. The method additionally includes generating a weight for edges of the directed graph according to a distribution of the datetime data in the columns and a usage index of a corresponding expression.

Abstract: Certain aspects of the present disclosure provide techniques for Scripting attack detection and mitigation. A method generally includes receiving a first report indicating a first violation for a first security policy applied to a first web application; identifying a first plurality of features associated with the first violation; classifying the first violation as a first JavaScript attack based on the first plurality of features; and taking action to mitigate the first JavaScript attack on the first web application.