Intuit, Inc.

Oracle International Corporation

William Taylor Laaser

Luis Felipe Cabrera

Massimo Mascaro

Jonathan Goldman

Per-Kristian G Halvorsen

James Alan Schneider

Rajalakshmi Ganesan

Gang Wang

Kevin M McCluskey

Alexander S Ran

Saikat Mukherjee

Anu Sreepathy

Cynthia Joann Osmon

Gerald Baron Huff

Cem Unsal

Mritunjay Kumar

Komal Bhatia

Michael J Graves

Scott D Cook

Hugh N Molotsi

Matthew A Lisowski

Arien C T Ferrell

Michael J Bertrand

Nicholas Philip Dearden

Timothy Glenn MacNary

Mithun Madadevan

Mithun Mahadevan

Certain aspects of the present disclosure provide techniques for optimizing a cost function of a deep learning algorithm. One example method generally includes executing, via a processing apparatus, the machine learning model, wherein the machine learning model can be optimized using gradient descent and evaluating output of the machine learning model using a cost function. The method further involves determining a gradient of the cost function and generating an auxiliary function based on the gradient. The method further involves identifying a root of the auxiliary function corresponding to a minimum point of the cost function, wherein calculation of the root is numerically stable and updating the machine learning model based on the root of the auxiliary function.

Methods of generating auxilary functions for use with machine learning methods

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.

System and method for increasing efficiency of gradient descent while training machine-learning models

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.

System and method for automatically generating calculations for fields in compliance forms

Methods, systems and articles of manufacture for using one or more predictive models to predict which tax matters are relevant to a particular taxpayer during preparation of an electronic tax return. A tax return preparation system accesses taxpayer data such as personal data and/or tax data regarding the particular taxpayer. The system executes a predictive model which receives the taxpayer data as inputs to the predictive model. The predictive model generates as output(s) one or more predicted tax matters which are determined to be likely to be relevant to the taxpayer. The system may then determine tax questions to present to the user based at least in part upon the predicted tax matters determined by the predictive model.

Methods systems and articles of manufacture for using a predictive model to determine tax topics which are relevant to a taxpayer in preparing an electronic tax return

A method involves scanning a symbol presented on a point of sale (POS) system including a POS processor; decoding the symbol to obtain purchase data and bidirectional connection data, where the bidirectional connection data describes a bidirectional connection; generating payment data using the purchase data; establishing the bidirectional connection with the POS system; sending the payment data to the POS system over the bidirectional connection; and receiving payment confirmation from the POS system over the bidirectional connection in response to the sending the payment data.

System and method to enable payment using mark generation and mobile device

Methods, systems and articles of manufacture for a method for generating a database of tax correlation data which can be used for tailoring a user experience in preparing an electronic tax return. A computing device accesses a data source having a plurality of data records. Each data record comprises a taxpayer attribute and a tax related aspect for a respective taxpayer. The computing device analyzes the plurality of data records and determines a correlation between the taxpayer attribute and the tax related aspect and determines a probability for the correlation. The computing device utilizes the probability for the correlation to determine a quantitative relevancy score for a tax matter, which can be incorporated into the tax correlation data of the life/knowledge module.

Methods systems and articles of manufacture for tailoring a user experience in preparing an electronic tax return

A method and system provides a tax refund confidence indicator to a user of a tax return preparation system, according to one embodiment. The method and system include receiving user current tax related data from a user and receiving historical tax related data associated with previously prepared tax returns. The method and system further includes generating estimated tax refund data and confidence score data indicative of the reliability of the estimated tax refund data. The method and system include providing the estimated tax refund data and the confidence score data to the user.

Method and technique to calculate and provide confidence score for predicted tax due/refund

Computer-implemented methods, articles of manufacture and computerized systems for identifying or alerting a user of certain data in electronic tax returns. A computerized tax return preparation system including a tax return preparation software application executed by a computing device receives first and second tax data and populates respective fields of the electronic tax return. The system executes a predictive model such as logistic regression, naive bayes, K-means clustering, clustering, k-nearest neighbor, and neural networks. First tax data is an input into the predictive model, which generates an output, which is compared with second tax data. An alert is generated when the second tax data does not satisfy pre-determined criteria relative to the first output generated by the predictive model. The same or other predictive model may be used as additional tax data is received for subsequent tax data analysis.

Predictive model based identification of potential errors in electronic tax return

A computer analytic system for allocating resources of an electronic tax return preparation system, the system includes an information module configured to collect taxpayer data of a user, the taxpayer data including an indicator of an increased likelihood that the user will abandon the electronic tax return preparation program. The system also includes a memory module configured to store the collected taxpayer data. The system further includes a retention module configured to analyze the collected taxpayer data and generate a resource allocation recommendation based on the collected taxpayer data.

Systems for allocating resources based on electronic tax return preparation program user characteristics

A system for calculating an estimated result for an electronic tax return to be prepared before a user begins to prepare the electronic tax return using an electronic tax return preparation program includes a server computer having a predictive model, and a user computer having a browser program. The user computer and the browser program are operatively coupled to the server computer and the predictive model by a network. The server computer is configured to obtain a first taxpayer datum associated with a taxpayer and execute the predictive model, which generates a predicted taxpayer datum for the taxpayer based on the first taxpayer datum. The server computer is configured to calculate the estimated result using the predicted taxpayer datum. The user computer is configured to display the estimated result to the user before the user begins to prepare the electronic tax return using the electronic tax return preparation program.

Methods, systems and computer program products for calculating an estimated result of a tax return

A non-transitory computer readable medium including instructions that, when executed by a processor, perform a method involving: receiving, by a point of sale (POS) system, purchase data for a customer; generating bidirectional connection data for the customer, where the bidirectional connection data describes a bidirectional connection; encoding a symbol with the purchase data and the bidirectional connection data; presenting the symbol to the customer; enabling the bidirectional connection in response to a connection request from the customer; receiving payment data from the customer over the bidirectional connection; comparing the payment data to the purchase data; and sending a payment confirmation to the customer over the bidirectional connection in response to a determination that the payment data satisfies the purchase data.

Growing community of inventors

Palo Alto, CA, United States of America

William Taylor Laaser