Transmission of a message based on the occurrence of a workflow event and the output of an externally augmented propensity model identifying a future financial requirement
First Claim
1. A method, comprising:
- scoring a business entity by applying at least one propensity model to data associated with the business entity to generate a score, wherein the data includes;
a first portion of the data that is created based on a financial management platform utilized by users associated with the business entity, wherein the financial management platform is configured to manage finances, anda second portion of the data that includes financial data of at least one owner of the business entity,wherein the data associated with the business entity matches at least a subset of the at least one propensity model, andwherein the at least one propensity model comprises a machine learning model trained using reconstructed data of a plurality of business entities,the reconstructed data comprises transactions contained in business entity data of the plurality of business entities prior to a specified date,the at least one propensity model built by applying a rule ensemble method to the reconstructed data of the plurality of business entities, and wherein the rules ensemble method comprises generating different rules, testing the rules against the reconstructed data, and ranking the different rules as determined by logistic regression, andthe at least one propensity model is trained to model how data of the business entity in a plurality of business entities relates to a future financial requirement of the business entity;
generating, based on the score of the business entity and using the at least one propensity model, a classification of a future financial requirement of the business entity, wherein the future financial requirement comprises a predicted future financial need of the business entity;
determining that the classification of the future financial requirement of the business entity meets a financial requirement threshold;
determining, using the first portion of data, that an aspect of the business entity meets a business activity threshold;
detecting that a workflow event has occurred on the financial management platform; and
in response to detecting the workflow event, determining the classification of the future financial requirement of the business entity meets the financial requirement threshold, and determining that the aspect of the business entity meets the business activity threshold, transmitting a message to a user of the business entity, the message containing an actionable offer for a financial loan, the actionable offer configured to be manipulated by a user in a graphical user interface.
1 Assignment
0 Petitions
Accused Products
Abstract
A method for transmitting a message based on the occurrence of a workflow event and the output of an externally augmented propensity model. The method includes scoring a business entity by applying a propensity model to data. The data includes a first portion created based on a platform utilized by users associated with the business entity, and a second portion that includes financial data of an owner of the business entity. The method includes generating, based on the score, a classification of a future financial requirement of the business entity, and determining that the classification meets a financial requirement threshold. Moreover, the method includes determining, using the first portion of data, that an aspect of the business entity meets a business activity threshold. Also, the method includes detecting that a workflow event has occurred on the platform, and, in response, transmitting a message to a user of the business entity.
42 Citations
27 Claims
-
1. A method, comprising:
-
scoring a business entity by applying at least one propensity model to data associated with the business entity to generate a score, wherein the data includes; a first portion of the data that is created based on a financial management platform utilized by users associated with the business entity, wherein the financial management platform is configured to manage finances, and a second portion of the data that includes financial data of at least one owner of the business entity, wherein the data associated with the business entity matches at least a subset of the at least one propensity model, and wherein the at least one propensity model comprises a machine learning model trained using reconstructed data of a plurality of business entities, the reconstructed data comprises transactions contained in business entity data of the plurality of business entities prior to a specified date, the at least one propensity model built by applying a rule ensemble method to the reconstructed data of the plurality of business entities, and wherein the rules ensemble method comprises generating different rules, testing the rules against the reconstructed data, and ranking the different rules as determined by logistic regression, and the at least one propensity model is trained to model how data of the business entity in a plurality of business entities relates to a future financial requirement of the business entity; generating, based on the score of the business entity and using the at least one propensity model, a classification of a future financial requirement of the business entity, wherein the future financial requirement comprises a predicted future financial need of the business entity; determining that the classification of the future financial requirement of the business entity meets a financial requirement threshold; determining, using the first portion of data, that an aspect of the business entity meets a business activity threshold; detecting that a workflow event has occurred on the financial management platform; and in response to detecting the workflow event, determining the classification of the future financial requirement of the business entity meets the financial requirement threshold, and determining that the aspect of the business entity meets the business activity threshold, transmitting a message to a user of the business entity, the message containing an actionable offer for a financial loan, the actionable offer configured to be manipulated by a user in a graphical user interface. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A system, comprising:
-
a hardware processor and memory; and software instructions stored in the memory and configured to execute on the hardware processor, which, when executed by the hardware processor, cause the hardware processor to; score a business entity by applying at least one propensity model to data associated with the business entity to generate a score, wherein the data includes; a first portion of the data that is created based on a financial management platform utilized by users associated with the business entity, wherein the financial management platform is configured to manage finances, and a second portion of the data that includes financial data of at least one owner of the business entity, wherein the data associated with the business entity matches at least a subset of the at least one propensity model, and wherein the at least one propensity model comprises a machine learning model trained using reconstructed data of a plurality of business entities, the reconstructed data comprises transactions contained in business entity data of the plurality of business entities prior to a specified date, the at least one propensity model built by applying a rule ensemble method to the reconstructed data of the plurality of business entities, and wherein the rules ensemble method comprises generating different rules, testing the rules against the reconstructed data, and then ranking the different rules as determined by logistic regression, and the at least one propensity model is trained to model how data of the business entity in a plurality of business entities relates to a future financial requirement of the business entity, generate, based on the score of the business entity and using the at least one propensity model, a classification of a future financial requirement of the business entity, wherein the future financial requirement comprises a predicted future financial need of the business entity, determine that the classification of the future financial requirement of the business entity meets a financial requirement threshold, determine, using the first portion of data, that an aspect of the business entity meets a business activity threshold, detect that a workflow event has occurred on the financial management platform, and in response to detecting the workflow event, determining the classification of the future financial requirement of the business entity meets the financial requirement threshold, and determining that the aspect of the business entity meets the business activity threshold, transmit a message to a user of the business entity, the message containing an actionable offer for a financial loan, the actionable offer configured to be manipulated by a user in a graphical user interface. - View Dependent Claims (11, 12, 13, 14, 15, 16, 17, 18)
-
-
19. A non-transitory computer readable medium storing instructions, the instructions, when executed by a computer processor, comprising functionality for:
-
scoring a business entity by applying at least one propensity model to data associated with the business entity to generate a score, wherein the data includes; a first portion of the data that is created based on a financial management platform utilized by users associated with the business entity, wherein the financial management platform is configured to manage finances, and a second portion of the data that includes financial data of at least one owner of the business entity, wherein the data associated with the business entity matches at least a subset of the at least one propensity model, and wherein the at least one propensity model comprises a machine learning model trained using reconstructed data of a plurality of business entities, the reconstructed data comprises transactions contained in business entity data of the plurality of business entities prior to a specified date, the at least one propensity model built by applying a rule ensemble method to the reconstructed data of the plurality of business entities, and wherein the rules ensemble method comprises generating different rules, testing the rules against the reconstructed data, and then ranking the different rules as determined by logistic regression, and the at least one propensity model is trained to model how data of the business entity in a plurality of business entities relates to a future financial requirement of the business entity; generating, based on the score of the business entity and using the at least one propensity model, a classification of a future financial requirement of the business entity, wherein the future financial requirement comprises a predicted future financial need of the business entity; determining that the classification of the future financial requirement of the business entity meets a financial requirement threshold; determining, using the first portion of data, that an aspect of the business entity meets a business activity threshold; detecting that a workflow event has occurred on the platform; and in response to detecting the workflow event, determining the classification of the future financial requirement of the business entity meets the financial requirement threshold, and determining that the aspect of the business entity meets the business activity threshold, transmitting a message to a user of the business entity, the message containing an actionable offer for a financial loan, the actionable offer configured to be manipulated by a user in a graphical user interface. - View Dependent Claims (20, 21, 22, 23, 24, 25, 26, 27)
-
Specification