Abstract: Feature randomization for securing machine learning models includes receiving an event, and altering, responsive to receiving the event, a threshold pseudo-randomly to generate an altered threshold value. Feature randomization further includes applying the altered threshold value to a threshold-dependent feature to generate an altered threshold-dependent feature value. The altered threshold-dependent feature value determined at least in part from the event. Feature randomization further includes executing a machine learning model, on the event and the altered threshold-dependent feature value, to generate a predicted event type for the event.

Abstract: Systems and methods for mapping an electronic document to a particular transaction category are disclosed. An example method may be performed by one or more processors of a categorization system and include receiving, from a user via an interface, an electronic document associated with a transaction between the user and a particular establishment, receiving, from the user via the interface, an image of the particular establishment, identifying in the image, using an image recognition engine, at least one of a sign or a symbol representative of the particular establishment, extracting, using an analytics module, location information from at least one of the image or a mobile device, determining, using the analytics module, a name of the particular establishment based on at least one of the location information or the at least one sign or symbol, and mapping the electronic document to a particular transaction category based on the determined name.

Abstract: A method scalably authorizes requests. A request to authorize access to a resource is received. A plurality of policies controlling the request is identified. The plurality of policies are concurrently processed. A decision for a policy is received. The decision is of a plurality of decisions corresponding to the plurality of policies. The policy is of the plurality of policies. The decision is determined using a machine learning model and the request. An aggregate decision is generated from the plurality of decisions. A token to access the resource is transmitted in response to the aggregate decision.

Abstract: A method including training, using accepted data having known labels, an untrained prediction model to generate a trained prediction model. The method also includes generating, using the trained prediction model, predicted labels for unknown data. The method also includes generating, using a confidence model, confidence scores for the predicted labels. The method also includes selecting, using the confidence scores, a subset of the unknown data and confident labels. The confident labels include ones of the predicted labels for the subset of the unknown data. The method also includes training, using the subset of the unknown data and the confident labels, the trained prediction model to generate an updated prediction model.

Abstract: Certain aspects of the present disclosure provide techniques for ranking users based on similarity. One example method generally includes receiving a request to view a list of users similar to a user based on personal information and receiving user data generated based on attribute data and financial data associated with the user comprising value data of the user. The method further includes obtaining clusters comprising value data of a plurality of users based on mapped data of the plurality of users and determining, by comparing the value data of the user data with the value data of the clusters, a cluster of vectors similar to the user data. The method further includes generating, based on a list of user identifiers using a distance function, a ranked list of similar users and transmitting the ranked list of similar users to a user device for display.

Abstract: A workflow construction system for constructing automation workflows that automate user specific processes. The workflow construction system may include a template library including workflow templates and pre-configured attributes. The workflow template can accelerate the design and construction of custom automation workflows. An orchestration layer included in the workflow construction system will also improve the performance of systems that execute the automation workflows by dynamically scaling the processing capacity, memory, and storage of servers and other systems hosting the model file instances of the automation workflows to ensure the available resources meet the demands of users completing processes using the automation workflows.

Abstract: A plurality of graph snapshots for a plurality of consecutive periodic time samples maps between connected components in consecutive graph snapshots and describes at least one feature of each connected component. A recursively-built tree tracks an evolution of one of the connected components through the plurality of graph snapshots, the tree including a root node representing the connected component at a final one of the consecutive periodic time samples and a plurality of leaf nodes branching from the root node. A plurality of paths is extracted from the tree by traversing the tree from the root node to respective ones of the plurality of leaf nodes. Each path contains data describing an evolution of a respective one of the connected components through time as indicated by evolution of the at least one feature of the respective one of the connected components.

Abstract: A workflow automation system that automates business tasks by executing task workflow models. The workflow automation system distributes actions to multiple clients based on roles and permissions to facilitate completion of manual and automated tasks included in the workflow models. The workflow automation system may pre-configure the roles and permissions to reduce the set up time for workflow model implementations of tasks. The workflow automation system improves the speed and efficiency of completing tasks relative to manual methods and other workflow automation tools.

Abstract: A method including transcribing, automatically, an ongoing stream of voice data into text phrases. The method also includes receiving an indication of a selected text phrase in the text phrases. The method also includes converting the selected text phrase to a selected phrase vector. The method also includes generating a subsequent text phrase, after the selected text phrase, from the ongoing stream of voice data, and adding the subsequent text phrase to the text phrases. The method also includes converting the subsequent text phrase to a subsequent phrase vector. The method also includes generating a similarity confidence score from the selected phrase vector and the subsequent phrase vector, using a machine learning model. The method also includes highlighting, responsive to the similarity confidence score exceeding a threshold value, the subsequent text phrase in the text phrases.

Abstract: A data management system stores data related to a plurality of users. The data management system initially stores the data in an encrypted format. The data management system automatically periodically re-encrypts the data in accordance with a re-encryption policy. The re-encryption policy includes re-encryption periodicity data defining a periodicity for automatically re-encrypting the data.

Abstract: This disclosure provides systems, methods and apparatuses for detecting anomalous activity in an electronic system. In some implementations, a system generates a set of model parameters based on a number (n) of historical datapoints in a dataset, where each datapoint represents activity detected in the electronic system over a respective period of time. The system receives a first new data point for the data set and generates a first test parameter based on a value of the first new datapoint and an average and a measure of spread of the n historical datapoints. The system further compares the first test parameter to the set of model parameters and determines whether the first new datapoint represents an anomaly based at least in part on the comparison.

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: Local data can be made available in a cloud computing environment. A persistent remote connection may be established between a processor and a server. The server may receive a request for data from an external device through a network. The request for data may be sent through the persistent remote connection from the server to a first executable process of the processor. The processor may obtain the data from an application being executed by the processor separately from the first executable process. The data may be sent through the persistent remote connection from the processor to the server. The server may send the data to the external device through the network in response to the request. The persistent remote connection may be maintained in an open state regardless of a status of the request for data.

Abstract: A computer-implemented method for generating explanations for a tax calculation or operation performed by tax preparation software is disclosed. A computing device executes a tax calculation engine in connection with the tax preparation software and operates on a tax calculation graph to perform a tax calculation. The tax calculation graph semantically describes data dependent tax operations comprising functional nodes connected to input nodes by one of a plurality of functions, wherein each tax operation is associated with one or more explanations. An explanation engine is executed to generate a narrative explanation from the one or more explanations associated with one of the tax operations and is presented to the user on the computing device.

Abstract: Systems and methods that may be configured to implement a nearest neighbor-based bank account validation process that may be used with electronic payments, transactions and or services.

Abstract: Certain aspects of the present disclosure provide techniques for detecting fraudulent transactions in a transaction processing system. An example method generally includes receiving a request to process a transaction. An input data set including a vector representing the transaction and a plurality of vectors representing historical transactions is generated. The input data set is divided into a plurality of ragged tensors corresponding to non-overlapping time segments of variable length and having a plurality of vectors associated with dates within each time segment A reduced input data set is generated by generating, for each respective ragged tensor of the plurality of ragged tensors, a respective representative vector using max pooling over vectors in the ragged tensor. A fraudulent transaction score is generated based on the reduced input data set using a fraud detection model. The transaction is processed based, at least in part, on the fraudulent transaction score.

Abstract: Certain aspects of the present disclosure provide techniques for privacy-preserving execution of a workflow in a software application. Embodiments include generally includes receiving homomorphically encrypted inputs from a client device corresponding to user-provided data needed to calculate a result for a step of a workflow in the software application. A result is calculated for the step of the workflow using the received homomorphically encrypted inputs. The calculated result is returned to the client device. The calculated result is homomorphically encrypted as a result of calculating the result using the received homomorphically encrypted inputs.

Abstract: Certain aspects provide techniques for disambiguating graph data. In one example, a method includes receiving entity data from a data source in a first format; converting the entity data in the first format to a second format, wherein the second format is a standardized input format for a disambiguation pipeline; determining a blocked data set from the entity data in the second format based on a blocking parameter, wherein: the blocked data set comprises data regarding a first plurality of entities, and the first plurality of entities is a subset of a second plurality of entities represented in the entity data from the data source; matching at least two entities in the first plurality of entities in the blocked data set; merging the at least two entities into a single entity; generating a unique ID for the single entity; and importing the single entity into a graph database.

Abstract: Certain aspects of the present disclosure provide techniques for performing computations on encrypted data. One example method generally includes obtaining, at a computing device, encrypted data, wherein the encrypted data is encrypted using fully homomorphic encryption and performing at least one computation on the encrypted data while the encrypted data remains encrypted. The method further includes identifying a clear data operation to perform on the encrypted data and transmitting, from the computing device to a server, a request to perform the clear data operation on the encrypted data, wherein the request includes the encrypted data. The method further includes receiving, at the computing device in response to the request, encrypted output from the server, wherein the encrypted output is of the same size and the same format for all encrypted data transmitted to the server.

Abstract: Certain aspects of the present disclosure provide techniques for performing finite rank deep kernel learning. In one example, a method for performing finite rank deep kernel learning includes receiving a training dataset; forming a set of embeddings by subjecting the training data set to a deep neural network; forming, from the set of embeddings, a plurality of dot kernels; combining the plurality of dot kernels to form a composite kernel for a Gaussian process; receiving live data from an application; and predicting a plurality of values and a plurality of uncertainties associated with the plurality of values simultaneously using the composite kernel.