Intuit, Inc.

Marko Rukonic

Wei W Wang

Wei Wang

Alexander S Ran

Christopher Z Lesner

James Robert Del Favero

Benjamin R Weiss

Chris Lee

Barron R Ernst

Eugene Krivopaltsev

George A Hansen

Suresh R Rao

Nicholas Augustine Mooney

Yuri Kapulkin

Alan De Robert d'Escragnolle

Robert W Cox

John Reed Flora

David Junzi Wu

Jessie Ann Haffey

Zhicheng Xue

Jim Del Favero

Eric King Loong Shiu

Hui Jin

Mitchell D Bayersdorfer

Keith Anders Olson

Marie L Hughes

Hung Yip Wu

Praveen Reddy Kasireddy

Levon Budagyan

Naren Sulur

Christopher Lesner

A method and system assist users of an electronic bookkeeping system to sort financial transactions into accounts representing bookkeeping categories. The method and system generate vectors representing the accounts and the merchants known to the bookkeeping system. The method and system generate compressed versions of the vectors by compressing the vectors. The method and system assist users to sort the financial transactions by analyzing the compressed vectors.

System and method for dimensionality reduction of vendor co-occurrence observations for improved transaction categorization

Certain aspects of the present disclosure provide techniques for determining similarities between businesses. One example method generally includes receiving a similarity query and receiving transaction data associated with a plurality of businesses for comparing the plurality of businesses. The method further includes generating a set of vectors representing the plurality of businesses based on the transaction data and generating a set of compact vectors based on the vectors by applying a dimensionality reduction technique. The method further includes generating based on the set of compact vectors, a similarity index and determining a response to the similarity query using the similarity index.

Responding to similarity queries using vector dimensionality reduction

Certain aspects of the present disclosure provide techniques for generating a human readable summary explanation to a user for an outcome generated by a complex machine learning model. In one embodiment, a risk assessment service can receive a request from a user in which a risk model of the risk assessment service performs a specific task (e.g., determining the level of risk associated with the user). Once the risk model determines the risk associated with the user, in order to comply with regulations from a compliance system, the risk model can provide a user with an explanation as to the outcome for transparency purposes.

Explainable complex model

A method and system assists users of an electronic bookkeeping system to sort financial transactions into accounts representing bookkeeping categories. The method and system generates vectors representing the accounts and the merchants known to the bookkeeping system. The method and system generates compressed versions of the vectors by compressing the vectors. The method and system assists users to sort the financial transactions by analyzing the compressed vectors.

A method may include generating a source transaction description, encoding, by an encoder model of a machine translation model executing on a computer processor, the source transaction description to create a context vector, decoding, by a decoder model of the machine translation model, the context vector to predict a target entity description, generating a transaction including the target entity description, detecting an acceptance, by a user, of an action performed on the transaction, in response to detecting the acceptance, updating a translation accuracy metric for the target entity description, determining that the updated translation accuracy metric satisfies a translation accuracy criterion, and in response to determining that the updated translation accuracy metric satisfies the translation accuracy criterion, adding the target entity description to golden entity descriptions.

Translating transaction descriptions using machine learning

A method and system groups user accounts in a financial management system based on the similarities of the financial transactions associated with the accounts. The method and system groups merchants involved in the financial transactions based on how financial transactions involving the merchants are sorted into groups of merchants. The method and system group users based on how the users sort financial transactions into their accounts. The method and system assist users to sort future financial transactions based on the groups of accounts, the groups of merchants, and the groups of users.

Method to use transaction, account, and company similarity clusters derived from the historic transaction data to match new transactions to accounts

Graphical user interfaces or visual representations of budgets and related systems and methods for visually presenting a budget and how consumer spending adheres to the budget. Budget elements or panels relate to budget categories, and respective sizes of budget elements indicate respective portions of income allocated to corresponding budget categories. Income amounts or desired savings amounts can be adjusted, in response to which sizes of the selected budget and savings elements are changed. After establishing a budget, the consumer purchases items. Corresponding budget elements are filled to indicate respective allocated amounts of income spent on respective budget elements by the consumer. An empty budget element indicates no money has been spent, a partially filled budget element indicates that some of the allocated income was spent, and a completely filled budget element indicates that all of the allocated income was spent. Overspending may be indicated by emphasizing the budget element.

Interactive budget display including dynamically adjustable budget elements

A method for error correction of a first misclassified transaction that includes receiving a request to correct the first misclassified transaction. The first misclassified transaction is associated with a first client accounting data store of a first client. The first misclassified transaction is associated with a first account, and the request is to change the first account to a second account. The method further includes generating a pattern for account correction based on the request, and applying the pattern to transactions to identify a second misclassified transaction. The transactions are associated with a second client accounting data store of a second client. The method further includes presenting a suggestion of a modification of the second misclassified transaction based on the pattern, and receiving an acceptance of the suggestion.

Error correction system for accountants

A method and system groups user accounts in a financial management system based on the similarities of the financial transactions associated with the accounts. The financial management system receives financial transaction data related to a plurality of financial transactions of a plurality of users. Each of the financial transactions is associated with an account of a user. The financial management system generates account characteristics vector data including, for each account, an account characteristics vector based on the financial transactions associated with the account. The financial management system groups the accounts by performing grouping analysis on the account characteristics vectors.

Method to determine account similarity in an online accounting system

A system and method for automated optimization of budgeted fund allocation to pay bills receives financial data including billing and income data. The data is ordered according to dates and amounts and the processed to determine payments to be made at certain dates, in order to ensure that minimum payments are satisfied. Amounts over the minimum owed for certain bills are paid when possible, in order to minimize future debt load. Amounts owed are paid, when warranted, in two or more portions on different dates separated by an income event. Payments made and overall financial status is reported to a consumer computing system associated with a consumer.

System and method for automated optimization of budgeted fund allocation to pay bills

A system and method for managing website scripts includes operations which provide for selection and automatic management of community contributed website scripts in order to provide efficient operation for consumer users and computing systems providing services on their behalf. Periodically, at least once during each refresh period, one or more website scripts are selected to be automatically performed on a biller website, based on a predetermined priority, and if the selected script performs successfully for a given user account, no further script operations are required to be performed on the same website for that particular user account, during that same refresh period. A system and method for managing website scripts further includes decommissioning operations which provide for automatic decommissioning of community contributed website scripts that are functioning below a predetermined minimum performance threshold level.

System and method for managing website scripts

Controlling access to customer data. A customer service agent is provided with indirect access to customer data through an intermediate computer such that it is not necessary for the customer service agent to ask questions about the received customer data or receive such data from the customer directly. Secure data access can be used to validate customers and streamline customer interaction and discussions with customer service agents since many questions a customer service agent may ask a customer directly during a discussion are already answered and known to the customer service agent before the customer speaks with the customer service agent. The customer can select which merchants receive customer data, and customer data can be entered manually or acquired by processing images of customer documents or cards such as personal identification or account cards containing information to be used during customer service discussions.

Methods systems and computer program products for managing access to customer data

A system and method for managing website scripts includes operations which provide for user contributed website scripts for use by consumer users and computing systems providing services on their behalf. User contributed website scripts are used to periodically gather user data. Following receipt of a user contributed website script, validation operations are performed in order to ensure that the user contributed website script operates properly. Once an initial determination is made that the website script operates properly, award points are awarded to the contributing user, and contribution points are assigned. If performance of the user contributed website script fails after initial acceptance, the number of contribution points associated with the user contributed website script is reduced. If the number of contribution points associated with a user contributed website script falls below a predetermined threshold, the user contributed website script is rendered unavailable for use.

Growing community of inventors

San Jose, CA, United States of America

Marko Rukonic