Intuit, Inc.

Colin R Dillard

Sambarta Dasgupta

Shashank Shashikant Rao

Sricharan Kallur Palli Kumar

Siddharth Ram

Shyam P Nukala

Anup Pramod Mutalik

Sricharan Kallur Kumar

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.

Hierarchical deep neural network forecasting of cashflows with linear algebraic constraints

Forecasts are provided based on dynamic model selection for different sets of time series. A model comprises a transformation and a prediction algorithm. Given a time series, a transformation is selected for the time series and a prediction algorithm is selected to make a forecast based on the transformed time series. Sets of time series are distinguished from each other based on diverse sparsities, temporal scales and other time series attributes. A model is dynamically selected based on time series attributes to increase forecasting accuracy and decrease forecasting computation time. The dynamic model selection is based on the creation of a meta-model from historical sets of historical time series.

Method and system of dynamic model selection for time series forecasting

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.

Model selection in a forecasting pipeline to optimize tradeoff between forecast accuracy and computational cost

This disclosure relates to forecasting when and whether an invoice is to be paid and indicating such forecasts to a user. An example system is configured to perform operations including determining, by a classification model, a first confidence as to whether an invoice is to be paid, determining, by a regression model associated with the classification model, a first time associated with a second confidence as to when the invoice is likely to be paid, and indicating, to a user, whether the invoice is to be paid based on the first confidence and the first time when the invoice is likely to be paid based on the second confidence. The regression model may include one or more gradient boosted trees to determine the first time. Different times associated with different confidences can be determined by different gradient boosted trees, with the specific tree corresponding to the associated confidence.

Indicating forecasts of invoice payments

The disclosed embodiments provide a system that facilitates testing of an insecure computing environment. During operation, the system obtains a real data set comprising a set of data strings. Next, the system determines a set of frequency distributions associated with the set of data strings. The system then generates a test data set from the real data set, wherein the test data set comprises a set of random data strings that conforms to the set of frequency distributions. Finally, the system tests the insecure computing environment using the test data set.

Testing insecure computing environments using random data sets generated from characterizations of real data sets

A method for cash forecasting creates a plurality of event streams associated with a user of an online accounting service, identifies a first pattern in a first event stream that is a commitment and a second pattern in a second event stream that is a repeated pattern, generates a characterization for each of the plurality of event streams based on each identified pattern for the event stream, predicts one or more expected cash payments and one or more corresponding expected dates for each of the event streams using the characterization for the event stream and a forecasting model, receives a query related to cash flow through an application program interface (API), and responds to the query based on the one or more of the expected cash payments, the corresponding expected dates, and the one or more measures of uncertainty, to the query.

Framework for cash-flow forecasting

The disclosed embodiments provide a system that facilitates selecting a message to be presented to users based on a statistically valid hypothesis test. During operation, the system runs a hypothesis test by presenting alternate versions of a message to a test set of users and receives user-feedback data. Next, the system obtains a significance level for the test and determines a number of independent data subsets associated with data from the test. The system subsequently uses the significance level and the number of independent data subsets to calculate an individual significance level for each independent data subset. The system then uses the individual significance levels to calculate an amount of user-feedback data required to achieve the significance level during the test, and selects one of the alternate versions of the message by analyzing the calculated amount of user-feedback data during the test. Finally, the system presents the selected version.

Growing community of inventors

Mountain View, CA, United States of America

Colin R Dillard