Abstract: Systems and methods for forecasting cashflows across one or more accounts of a user disclosed. One example method may include retrieving a data set for each of a plurality of accounts from a database, constructing a graph including a plurality of nodes linked together by a multitude of edges, wherein each node identifies a time series value corresponding to one of the accounts, and each edge indicates a time series value of a corresponding set of transactions occurring between a corresponding pair of accounts, determining a plurality of constraints, determining a specified loss function based on the plurality of constraints, back-propagating a derivative of the specified loss function into a deep neural network (DNN) to determine a set of neural network parameters, forecasting, using the DNN, a time sequence for one or more of the nodes and one or more of the edges, and providing the forecasted time sequences to the user.

Abstract: Systems and methods for forecasting future values of data streams are disclosed. One example method may include receiving information characterizing each of a plurality of forecasting models, retrieving historical data for each of a plurality of data streams, determining one or more constraints, dynamically selecting one of the plurality of forecasting models for each of the data streams based on accuracy metrics for the forecasting models, estimating cost metrics associated with each forecasting model, dynamically selecting the forecasting model based at least in part on the accuracy metrics, the cost metrics, and the determined constraints, and forecasting a first subsequent value of each data stream using the corresponding selected forecasting model.

Abstract: A method including establishing, using electronic transactions of a user, a geo-temporal trajectory of the user. The method also includes forming a first data structure by sub-dividing the geo-temporal trajectory into segments including subsets of the electronic transactions along the geo-temporal trajectory. Sub-dividing is performed with respect to a selected feature. The method also includes gathering, for a subset of the segments, a corresponding labeled dataset of transactions within the electronic transactions to generate a second data structure. The method also includes applying, as input, the second data structure to a machine learning classifier. The method also includes receiving, from the machine learning classifier, an assignment of disambiguated labels to the electronic transactions. The method also includes storing, automatically in a financial management application, the disambiguated labels as assigned to the electronic transactions.

Abstract: One or more embodiments provide for a method. The method includes receiving a document including text. The method also includes receiving different definitions of a position in the document of an identifier-value pair within the text. The identifier-value pair includes an identifier identifying an information type in the text and a value including an entry of the information in the text. The method also includes determining which of the different definitions correctly point to the position to form a number of correct definitions. Each of the different definitions correctly points to the position when the identifier-value pair is found on a first attempt using a definition of the different definitions to search for the identifier-value pair. The method also includes, responsive to the number of correct definitions at least matching a threshold value, issuing a command to perform data scraping on the document to extract the value of the identifier.

Abstract: Embodiments disclosed herein relate to a method of writing a transaction to a data store having one or more data tables. An application agent receives transaction data for a first transaction of a first type. Application agent attempts to write the first transaction of the first type to a data table in the data store, provided that a transaction of the first type has been committed to the data store. Application agent scans a plurality of additional data stores for previously committed transactions of the first type Application agent determines additional transactions of another type that are co-located in a data table. Application agent ranks the additional transactions of the other type. Application agent identifies a data table in the data store to which a top ranking additional transaction of the other type has been committed. Application agent writes the first transaction to identified data table in the data store.

Abstract: A method includes executing, multiple times, a target application with at least one test input dataset to obtain multiple test output datasets. The test output data sets each include multiple field values for multiple fields. The method further includes comparing the field values with at least one validated output dataset to assign the fields into a match class, an ignore class, and an unknown class, extracting, from the comparing, a field property for a first subset of the fields in the match class, and generating a test result by adding, to the test result, whether a first subset of the field values corresponding to the first subset of the fields satisfies a corresponding field property, and ignoring a second subset of the a second subset of fields classified in the ignore class. The method further includes presenting the test result.

Abstract: A method for generating a business health score of a business entity that includes identifying tools used to manage the business entity, obtaining business information from the tools, filtering the business information into at least one data category to obtain categorized business information, populating the categorized business information into a data silo, and analyzing, by a computer processor, the categorized business information in the data silo to create a composite business factor. The method also includes applying an algorithm to the composite business factor to generate a result, generating, based on the result, the business health score of the business entity, and providing the business health score to an interested entity.

Abstract: The invention relates to a method for documenting subjects using hash chains. The method includes receiving a subject data write request including one or more subject attribute values, generating a fingerprint from a current last block of a hash chain, and generating a payload from the subject data, the payload including the one or more subject attribute values and one or more keys identifying the one or more subject attribute values. The method further includes appending a block to the hash chain. The appended block includes the payload and the fingerprint.

Abstract: A method and processing system for managing user access to one or more resources is disclosed. A central service may receive an access change request message regarding a user. The access change request message may include a user identifier, a user role, and an access action for the user. Example access actions may include adding or removing user access with respect to a resource. The central service may determine which resources are associated with the user role and transmit one or more event messages to the resources to implement the access actions. The resources may send acknowledgement messages to the central service to confirm that the access actions have been completed.

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: Aspects of the disclosure describe improving identification of product solutions. An example method includes transcribing in real-time a conversation between a user and an agent into a speech text, processing digital data of the speech text associated with a topic, including parsing the speech text into one or more words and determining collocation information among the one or more words in the speech text. The method also includes providing the one or more words and the collocation information as a first input set to a machine learning engine configured to recommend one or more product solutions from a library of product solutions, generating a recommendation of one or more product solutions for a user based on recommendation parameters for the library of product solutions, and providing the recommendation.

Abstract: A computer-implemented system and method for generating a minimum-cost circulation topology in a mesh network is provided. The system comprises one or more processors configured to receive a service request from a client computer and identify a group of services for the service request. The one or more processors are further configured to iteratively query a global registry for each of the group of services to obtain respective groups of dependent service instances, generate an adjacency table including a plurality of service dependency paths identified from the respective groups of dependent service instances. The system determines a minimum-cost service dependency path by applying a predetermined cost algorithm on the adjacency table and executing a first service instance of the minimum-cost service dependency path and route the service request to the second service instance in the dependency path.

Abstract: Certain aspects of the present disclosure provide techniques for facilitating text inputs with long-tail keywords from a user in a social question and answer (Q&A) application. One example method generally includes receiving, at a server, a text input from the user at a client computer, and applying, a predictive model to the text input. The method further includes determining based on the predictive model, an increase in user traffic that is predicted to be generated from the text input and determining, a user interface (UI) to be generated for display to the user for subsequent interaction based on the increase in user traffic. The method further includes sending the UI to the client computer and receiving a subsequent text input from the client computer.

Abstract: Aspects of the present disclosure provide techniques for efficient location tracking. Embodiments include receiving a device location from a mobile device. Embodiments include identifying a plurality of region definitions and selecting a set of region definitions from the plurality of region definitions based on a proximity of a location of each region definition of the plurality of region definitions to the device location. Embodiments include generating a provisional region definition based on a location of a region definition of the set of region definitions that is farthest from the device location and including the provisional region definition in the set of region definitions. Embodiments include providing the set of region definitions to the mobile device for provisioning and refraining from requesting device locations from the mobile device until receiving a notification from the mobile device that the mobile device has exited a provisional region defined by the provisional region definition.

Abstract: A computer-implemented method for collaboratively preparing an electronic tax return includes a host computer receiving a request from a first user for a collaborative tax preparation session through tax preparation software utilized by the first user to prepare an electronic tax return. The method also includes the host computer sending a message through a second network to a second computing device of a second user, inviting the second user to participate in the collaborative tax preparation session with the first user. The method further includes the host computer receiving a reply from the second computing device, including agreement by the second user to participate in the session. Moreover, the method includes the host computer establishing the collaborative tax preparation session. During the collaborative tax preparation session, the host computer receives tax-related information from the second computing device, and sends the received tax-related information to the first computing device.

Abstract: A method includes obtaining data related to a plurality of historical transactions, where each historical transaction is associated with a label based on a click stream created by the first user, generating a vector of features from the data related to each historical transaction, training, using the vectors and labels, a multinomial classifier to generate a probability that a specific transaction belongs to a specific classification with respect to income, obtaining data related to a new transaction from a financial stream for a second financial account of a second user of the financial service, generating a new vector of features from the data related to the new transaction, determining a classification with respect to income for the new transaction, and presenting the classification to the second user for review in a view of a graphical user interface.

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: At least one processor may ingest transaction data of a user logged into a user account of a personal financial management (PFM) system. The transaction data may include descriptions of a plurality of transactions made using an account of the user. The at least one processor may scan the descriptions to identify, for each of the plurality of transactions, text indicative of at least one data provider. The at least one processor may compare the text with known data provider information to identify at least one data provider involved with at least one of the plurality of transactions. The at least one processor may link the user account to the at least one data provider identified by the comparing. The linking may cause data processed by the at least one data provider to be processed by the PFM system.

Abstract: Systems and methods that may be used to implement overlapping data caching for object application program interfaces (APIs). A unique identifier may be assigned to each sub-component of an object API request. The unique identifiers may be used to determine if sub-components of one object API request overlaps with a sub-component of a prior different request such that a data response for the prior different request can be retrieved from the cache and used as part of the data response for the current object API request.

Abstract: Techniques are disclosed for determining application experience of a user. One embodiment presented herein includes a computer-implemented method, which includes receiving, at a computing device, eye tracking data of a user interacting with at least a first page of an application. The computer-implemented method further includes determining, based at least on the eye tracking data, at least a current user experience regarding the first page. The computer-implemented method further includes predicting, based on evaluating the current user experience, that the user is likely to discontinue use of the application. The computer-implemented method further includes determining, based at least on the prediction, an intervention that reduces a likelihood of the user discontinuing use of the application, and interacting with the user according to the intervention.