Abstract: A computer-implemented method is provided to perform text classification with a neural network system. The method includes providing a computing device to receive input datasets including user input question text and feed the datasets to the neural network system. The neural network system includes one or more neural networks configured to extract and concatenate character-based features, word-based features from the question datasets and clickstream embeddings of clickstream data to form a representation vector indicative of the question text and user behavior. A representation vector is fed into fully connected layers of a feed-forward network. The feed-forward network is configured to predict a first class and a second class associated with respective user input questions based on the representation vector.

Abstract: Systems and methods for validating credentials are disclosed. One example method, performed by one or more processors of a computing device associated with a neural network, includes training the neural network to infer validity information for encrypted credentials received from a credential source, wherein the validity information is inferred without decrypting the encrypted credentials, receiving a first encrypted credential from the credential source, generating an encrypted validity indicator for the first encrypted credential based on the validity information inferred by the neural network, and providing the encrypted validity indicator to the credential source.

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: Systems and methods for automatically identifying problem-relevant sentences in a transcript are disclosed. In an example method, a transcript may be received of a first support call. A region of the first support call transcript may be identified, and first customer utterances may be detected in the region using a trained classification model. A trained regression model may estimate a relevancy to the problem statement of each of the first customer utterances, and one or more most problem-relevant statements may be selected from the first customer utterances, based on the estimated relevancies.

Abstract: A method may include obtaining, over a network from a financial institution and using login credentials of a user, transactions corresponding to the user, calculating average transaction amounts for merchants based on the transactions, generating a spending propensity score for a category using a harmonic mean of amounts in a subset of the transactions corresponding to the category, generating, for the category, spending match scores between the spending propensity score and the average transaction amounts for the merchants, and recommending a merchant to the user using the spending match scores.

Abstract: A method may include creating a task inbox corresponding to an email address. The email address may include a domain name corresponding to a computer program. The method may further include receiving, at the task inbox, emails from agents of an organization. The agents may include an agent. The emails may include an email from the agent. The method may further include extracting, from the email, a verb, a due date, and a client, determining that the verb is an actionable verb, in response to determining that the verb is an actionable verb, generating, from the email and within the computer program, a task including the due date and the client, and assigning, in the computer program, the task to the agent.

Abstract: This disclosure relates to systems and methods for identifying fraudulent email addresses associated with an electronic payment service. In some implementations, a computing device receives an email with a prefix having a number of characters and characterized by a prefix length indicative of the number of characters in the prefix. The computing device identifies each of a number of bigrams is identified within the prefix, and determines a row and column distance for each bigram between two consecutive characters of the bigram as positioned on a keyboard. The computing device calculates a Euclidean distance between the two consecutive characters of the bigram based on the row and column distances, and determines a normalized distance based on the prefix length and an average of the Euclidean distances calculated for the number of bigrams in the prefix. The normalized distance is compared with a value to classify the email as suspicious or as not suspicious.

Abstract: A system for facilitating user interaction with a tax return preparation program includes a completion graph parser configured to identify a portion of a tax return completion graph corresponding to a tax topic. The system also includes a query object creator configured to analyze and assign a node in the portion as a query object property. The system further includes a natural language synthesis engine configured to map the property to a first natural language question. Moreover, the system includes a natural language analysis engine configured to analyze user input and to identify a characteristic that maps to the property based on the user input. In addition, the system includes a runner interface configured to modify the query object based on the characteristic, update the tax return completion graph based on the modified query object, and analyze the updated tax return completion graph to determine whether it is complete.

Abstract: Certain aspects of the present disclosure provide techniques for providing a graphical user interface to assist a user of an application programming interface (API). Embodiments include determining that the user has selected an attribute of the API within an API explorer. The API explorer may be displayed with a developer interface of a web application. Embodiments further include identifying a user interface component of the web application that is related to the attribute of the API. Embodiments further include displaying an indication within the developer interface that the user interface component is related to the attribute of the API.

Abstract: Certain aspects of the present disclosure provide techniques for detecting personally identifiable information, including: receiving a plurality of text strings, each text string of the plurality of text strings associated with a user support session; providing the plurality of text strings to one or more bidirectional long short-term memory (BiLSTM) neural network models; receiving output from the one or more BiLSTM neural network models, the output indicating one or more text data elements in the plurality of text strings comprising predicted personally identifiable information; redacting the one or more text data elements comprising the predicted personally identifiable information from the plurality of text strings to form redacted text strings; and providing, to a data repository, the redacted text strings.

Abstract: Systems and methods of the present disclosure provide processes for determining how much to adjust machine-learning parameter values in a direction of a gradient for gradient-descent steps in training processes for machine-learning models. Current parameter values of a machine-learning model are vector components that define an initial estimate for a local extremum of a cost function used to measure how well the machine-learning model performs. The initial estimate and the gradient of the cost function for the initial estimate are used to define an auxiliary function. A root estimate is determined for the auxiliary function of the gradient. The parameters are adjusted in the direction of the gradient by an amount specified by the root estimate.

Abstract: A method and system to learn new forms to be incorporated into an electronic document preparation system, or to learn the behavior of existing systems, receive form data related to a new form having a plurality of data fields that expect data values based on specific functions. The method and system gather training set data including previously filled forms having completed data fields corresponding to the data fields of the new form. The method and system include multiple analysis modules that each generate candidate functions for providing data values for the data fields of the new form. The method and system evaluate the candidate functions from each analysis technique and select the candidate functions that are most accurate based on comparisons with the training set data.

Abstract: A method may include obtaining interactions between users and items, and calculating, for each edge in a bipartite graph, an edge weight using an inverse of the degree of a user node connected to the edge and an inverse of the degree of an item node connected to the edge. The bipartite graph includes user nodes corresponding to the users and item nodes corresponding to the items. The method may further include identifying paths each including an edge connecting the target user node and a common item node, an edge connecting a neighboring user node and the common item node, and an edge connecting the neighboring user node and a neighboring item node. The method may further include calculating, using the edge weights calculated for the edges, scores for the paths, and recommending, to the target user and using the scores for the paths, a recommended item.

Abstract: A method may be used to predict a business' category by analyzing the business' vendors. A neural network architecture may be trained via supervised learning to predict categories for businesses based on listed vendors. The neural network may be used to classify uncategorized businesses within an accounting software database. A list of factors associated with a business' success may be generated by analyzing, aggregating and ranking factors determined to be relevant to a business based on its categorization. The factors associated with the business' success may be related to the products and/or services offered by the business and the format of which those products and/or services are offered by the business. The factors may also be related to the products and/or services purchased by the business from a vendor and the format of which those products and/or services are purchased from the vendor.

Abstract: A method and system for generation of a customized financial document template in a financial management system, according to one embodiment. The method and system includes receiving a financial document that includes a plurality of data entries, according to one embodiment. The method and system includes mapping the plurality of data entries to a plurality of data fields of the financial management system, according to one embodiment. Mapping the plurality of data entries includes identifying characteristics of each of the plurality of data entries, and determining a relevance of the plurality of the data fields to the plurality of the data entries, at least partially based on the characteristics of the plurality of data entries, according to one embodiment. The method and system includes populating a custom financial document template, at least partially based on the mapping of the plurality of data entries to the plurality of data fields.

Abstract: Aspects of the present disclosure provide techniques for classifying a trip. Embodiments include receiving, from a plurality of users, a plurality of historical trip records. Each of the plurality of historical trip records may comprise one or more historical trip attributes and historical classification information. Embodiments include training a predictive model, using the plurality of historical trip records, to classify trips based on trip records. Training the predictive model may comprise determining a plurality of hot spots based on the historical trip records, each of the plurality of hot spots comprising a region encompassing one or more locations, and associating, in the predictive model, the plurality of hot spots with historical classification information. Embodiments include receiving, from a user, a new trip record comprising a plurality of trip attributes related to a trip and using the predictive model to predict a classification for the trip based on the trip record.

Abstract: An integrated development environment (IDE) that may provide compile-time validation, and incremental compilation and linking of multiple schema resources for a query language such as e.g., GraphQL.

Abstract: Systems, methods and articles of manufacture for generating a sub-graph of a tax calculation graph usable by a tax calculation engine to perform tax calculation operations. The system includes a computing device, a data store in communication with the computing device and a tax preparation software application executable by the computing device. The system comprises a tax calculation graph and a sub-graph engine which executes on the computing device. The sub-graph engine is configured to generate a sub-graph of the tax calculation graph based upon a target node and one or more user enterable nodes selected from the nodes of the tax calculation graph. The sub-graph engine analyzes the tax calculation graph in view of the target node and user enterable nodes and generates a sub-graph which excludes all nodes which are not necessary to calculate the target node.

Abstract: Certain aspects of the present disclosure provide techniques for providing sentiment analysis of content. In order to determine the overall sentiment of content, a request is received by a sentiment analyzer, which then identifies a content identification number and retrieves comments associated with the content identification number. The sentiment analyzer pre-processes the comments, which includes removing all personal identifying information from the comments. The sentiment analyzer sends the pre-processed comments to a natural language processing service, and in turn, receives sentiment indications corresponding to the comments provided. Based on the sentiment scores, the sentiment analyzer generates a sentiment analysis and displays the sentiment analysis in the graphical user interface generated by the sentiment analyzer.

Abstract: Certain aspects of the present disclosure provide techniques for displaying sentiment of a user text comment. One example method generally includes receiving a text comment comprising a sequence of words, providing a vector sequence representing the sequence of words to a sentiment model configured to output a sequence of sentiment scores for the vector sequence and providing cleaned text to a topic module configured to output relevance scores. The method further includes receiving, from the sentiment model, the sequence of sentiment scores for the vector sequence and receiving, from the topic module, the relevance scores for the cleaned text. The method further includes determining, final sentiment scores for each word of the sequence of words and generating a sentiment visualization for the sequence of words showing the final sentiment scores corresponding to each word of the sequence of words.