Application processing and decision systems and processes

• US 7,970,698 B2
• Filed: 08/27/2004
• Issued: 06/28/2011
• Est. Priority Date: 08/27/2003
• Status: Active Grant

• Current Assignee: Equifax, Inc.
• Original Assignee: Equifax, Inc.
• Inventors: Gupta, Sandeep, Horton, Dennis, Dixon, Thresa, Reddy, Sudhakar, Reid, James, Garten, Scott, Lu, Shen, Grice, Lee, Hall, Christian
• Primary Examiner(s): Kazimi; Hani
• Assistant Examiner(s): Ali; Hatem
• Application Number:
  US10/546,931
• Publication Number:
  US 20070022027A1
• Time in Patent Office: 2,496 Days
• Field of Search: 705/38
• US Class Current: 705/38
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 20/10 specially adapted for electronic funds transfer [EFT] systems; specially adapted for home banking systems
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/02 Banking, e.g. interest calculation or account maintenance credit or loans G06Q40/03
• CPC Class Codes: G06Q 40/03 Credit; Loans; Processing thereof

Abstract

The present invention relates to automated decisioning for a credit request associated with an applicant. Information associated with an applicant is received. Data associated with the applicant is received from at least one data source. A user interface is configured to allow a user to provide a definition of decision rules in a near-natural language. Information associated with the decision rules is determined based on the definition of the decision rules. A selection of rule flow information associated with the decision rules is received through the user computer interface. A decision is generated based on the information associated with the applicant, data associated with the applicant from the at least one data source, the information associated with the decision rules, and the selection of information associated with decision rules. The decision is displayed.

Claims

1. A method for generating a rule for automated credit request decisioning, comprising:

receiving information associated with an applicant through a user interface;

configuring, by a server device, the user interface to allow a user to define a plurality of decision rules in a near-natural language;

receiving the plurality of decision rules in the near-natural language, the plurality of decision rules being received from the user through the user interface;

determining information associated with the plurality of decision rules based on the plurality of decision rules in the near-natural language;

generating a decision flow in response to receiving an identification from the user through the user interface of a flow element, of a decision block, and of a flow path for connecting to at least one of the decision block or the flow element, the decision flow comprising the flow element, the decision block, and the flow path;

receiving data associated with the applicant from at least one data source;

determining, by the server device, a decision for the applicant based on the information associated with the applicant, the data associated with the applicant from at least one data source, the information associated with the plurality of decision rules determined based on the plurality of decision rules in the near-natural language, and the decision flow, wherein determining the decision for the applicant comprises applying in accordance with the decision flow an executable version of the information associated with the plurality of decision rules in the near-natural language to the data associated with the applicant from at least one data source; and

providing the decision to the user interface.

2. The method of claim 1, wherein the user interface comprises a graphical user interface having an object associated with at least one of the plurality of decision rules, the method further comprising:

receiving, through the graphical user interface, a selection by the user of information associated with the at least one of the plurality of decision rules by receiving a position of the object.

3. The method of claim 2, wherein receiving the position of the object comprises receiving a signal associated with positioning the object on the graphical user interface, wherein the object is associated with the at least one of the plurality of decision rules.

4. The method of claim 1, wherein the applicant is one of:

an individual, an entity, a business, or a commercial institution.

5. The method of claim 1, wherein information associated with the plurality of decision rules comprises at least one of the following:

an attribute, a criteria, a workflow, a rule hierarchy, a workflow hierarchy, credit data associated with an applicant, a score, a statistical model, a threshold, a risk factor, information associated with at least one attribute, information associated with at least one criteria, information associated with a process performed by an entity, information associated with a business associated with an entity, and information associated with an industry associated with an entity.

6. The method of claim 1, further comprising:

applying at least one of the plurality of decision rules to at least a portion of the information associated with the applicant to obtain an outcome associated with the at least one of the plurality of decision rules;

generating a test outcome associated with the at least one of the plurality of decision rules; and

displaying the test outcome on the user interface.

7. The method of claim 6, wherein generating the test outcome associated with the at least one of the plurality of decision rules further comprises:

modifying the at least one of the plurality of decision rules based at least in part on information associated with the outcome.

8. The method of claim 6, further comprising:

receiving a selection of information associated with an alternative decision rule through the user interface;

generating an alternative decision rule based at least on the selection of information associated with the alternative decision rule through the user interface;

applying the alternative decision rule to at least a portion of the information associated with the applicant, wherein an alternative outcome associated with the alternative decision rule is obtained; and

displaying the alternative outcome on the user interface.

9. The method of claim 1, wherein the decision comprises at least one of:

denial of a credit line;

granting an approval of a credit line;

denial of a loan;

granting approval of a loan;

or

granting approval for providing the applicant with an offer of credit.

10. The method of claim 1, further comprising receiving through a template associated with the user interface the flow element, the decision block, and the flow path.

11. The method of claim 10, wherein the template comprises at least one of the following:

information associated with a user'"'"'s business, information associated with a user'"'"'s industry, information associated with a prospective customer of a user, information associated with a current customer of a user, information collected by a user, and information obtained by a user.

12. The method of claim 1, wherein the user interface comprises at least one of the following:

information associated with a user'"'"'s industry, information associated with a user'"'"'s business, information associated with a prospective customer of a user, information associated with a current customer of a user, information collected by a user, and information obtained by a user.

13. The method of claim 1, wherein receiving information associated with an applicant through the user interface comprises at least one of the following:

receiving information from an applicant, receiving information entered by an applicant, receiving information from a device associated with an applicant, receiving information from a data source associated with an applicant, and receiving information selected by an applicant.

14. The method of claim 1, wherein receiving data associated with an applicant from at least one data source comprises at least one of the following:

receiving information from a financial institution, receiving information from a credit provider, receiving information from a database, and receiving information from a credit reporting database.

15. The method of claim 1, wherein data associated with an applicant comprises at least one of the following:

identity information associated with the applicant, access information to authorize access to credit data from at least one credit reporting agency, information associated with an applicant from at least one risk analysis data source, contact information associated with an applicant, name, current address, social security number, date of birth, an address, a name of a co-applicant, information associated with an applicant'"'"'s spouse, information associated with an applicant'"'"'s driver license, information associated with an applicant'"'"'s employer, and information associated with applicant'"'"'s income.

16. The method of claim 1, wherein data associated with an applicant comprises at least one of the following:

credit reporting data, risk analysis data, check processing service data, blue book data, regional consumer exchange data, and commercial data.

17. A non-transitory computer-readable medium for generating a rule for automated credit request decisioning, comprising program code executable by a processor, the program code comprising:

program code for receiving information associated with an applicant through a user interface;

program code for receiving data associated with the applicant from at least one data source;

program code for configuring the user interface to allow the user to define a plurality of decision rules in a near-natural language;

program code for determining information associated with the plurality of decision rules based on the plurality of decision rules in the near-natural language defined by the user;

program code for generating a decision flow in response to receiving an identification from the user through the user interface of a flow element, of a decision block, and of a flow path for connecting to at least one of the decision block or the flow element, the decision flow comprising the flow element, the decision block, and the flow path;

program code for determining a decision for the applicant based on the information associated with the applicant, the data associated with the applicant from at least one data source, the information associated with the plurality of decision rules determined based on the plurality of decision rules in the near-natural language, and the decision flow, wherein program code for determining the decision for the applicant comprises program code for applying in accordance with the decision flow an executable version of the information associated with the plurality of decision rules in the near-natural language to the data associated with the applicant from at least one data source; and

program code for providing the decision to the user interface.

18. The non-transitory computer-readable medium of claim 17, further comprising:

program code for providing the user interface that comprises a graphical user interface having an object associated with at least one of the plurality of decision rules; and

program code for receiving, through the graphical user interface, a selection by the user of information associated with the at least one of the plurality of decision rules by receiving a position of the object.

19. The non-transitory computer-readable medium of claim 18, wherein program code for receiving, through the graphical user interface, a selection by the user of information associated with the at least one of the plurality of decision rules by receiving a position of the object comprises program code for receiving a signal associated with positioning the object on the graphical user interface, wherein the object is associated with the at least one of the plurality of decision rules.

20. The computer-readable medium of claim 17, wherein the applicant is one of:

an individual, an entity, a business, or a commercial institution.

21. The non-transitory computer-readable medium of claim 17, wherein information associated with the plurality of decision rules comprises at least one of the following:

an attribute, a criteria, a workflow, a rule hierarchy, a workflow hierarchy, credit data associated with an applicant, a score, a statistical model, a threshold, a risk factor, information associated with at least one attribute, information associated with at least one criteria, information associated with a process performed by an entity, information associated with a business associated with an entity, and information associated with an industry associated with an entity.

22. The non-transitory computer-readable medium of claim 17, further comprising:

program code for applying at least one of the plurality of decision rules to at least a portion of the information associated with the applicant to obtain an outcome associated with the at least one of the plurality of decision rules;

program code for generating a test outcome associated with the at least one of the plurality of decision rules; and

program code for displaying the test outcome on the user interface.

23. The non-transitory computer-readable medium of claim 22, wherein program code for generating the test outcome associated with the at least one of the plurality of decision rules further comprises:

program code for modifying the at least one of the plurality of decision rules based at least in part on information associated with the outcome.

24. The non-transitory computer-readable medium of claim 22, further comprising:

program code for receiving a selection of information associated with an alternative decision rule through the user interface;

program code for generating an alternative decision rule based at least on the selection of information associated with the alternative decision rule through the user interface;

program code for applying the alternative decision rule to at least a portion of the information associated with the applicant, wherein an alternative outcome associated with the alternative decision rule is obtained; and

program code for displaying the alternative outcome on the user interface.

25. The non-transitory computer-readable medium of claim 17, wherein the decision comprises at least one of:

denial of a credit line;

granting an approval of a credit line;

denial of a loan;

granting approval of a loan;

or granting approval for providing the applicant with an offer of credit.

26. The non-transitory computer-readable medium of claim 17, further comprising program code for receiving through a template associated with the user interface the flow element, the decision block, and the flow path.

27. The non-transitory computer-readable medium of claim 26, wherein the template comprises at least one of the following:

information associated with a user'"'"'s business, information associated with a user'"'"'s industry, information associated with a prospective customer of a user, information associated with a current customer of a user, information collected by a user, and information obtained by a user.

28. The non-transitory computer-readable medium of claim 17, wherein the user interface comprises at least one of the following:

information associated with a user'"'"'s industry, information associated with a user'"'"'s business, information associated with a prospective customer of a user, information associated with a current customer of a user, information collected by a user, and information obtained by a user.

29. The non-transitory computer-readable medium of claim 17, wherein program code for receiving information associated with an applicant through the user interface comprises at least one of the following:

program code for receiving information from an applicant, program code for receiving information entered by an applicant, program code for receiving information from a device associated with an applicant, program code for receiving information from a data source associated with an applicant, and program code for receiving information selected by an applicant.

30. The non-transitory computer-readable medium of claim 17, wherein program code for receiving data associated with an applicant from at least one data source comprises at least one of the following:

program code for receiving information from a financial institution, program code for receiving information from a credit provider, program code for receiving information from a database, and program code for receiving information from a credit reporting database.

31. The non-transitory computer-readable medium of claim 17, wherein data associated with an applicant comprises at least one of the following:

identity information associated with the applicant, access information to authorize access to credit data from at least one credit reporting agency, information associated with an applicant from at least one risk analysis data source, contact information associated with an applicant, name, current address, social security number, date of birth, an address, a name of a co-applicant, information associated with an applicant'"'"'s spouse, information associated with an applicant'"'"'s driver license, information associated with an applicant'"'"'s employer, and information associated with applicant'"'"'s income.

32. The non-transitory computer-readable medium of claim 17, wherein data associated with an applicant comprises at least one of the following:

credit reporting data, risk analysis data, check processing service data, blue book data, regional consumer exchange data, and commercial data.

33. A system for generating a rule for automated credit request decisioning, comprising:

a processor for executing stored instructions to

receive information associated with an applicant through a user interface;

receive data associated with the applicant from at least one data source;

configure the user interface to allow the user to define a plurality of decision rules in a near-natural language;

determine information associated with the plurality of decision rules based on the plurality of decisions rules in the near-natural language;

generate a decision flow in response to receiving an identification from the user through the user interface of a flow element, of a decision block, and of a flow path for connecting to at least one of the decision block or the flow element, the decision flow comprises the flow element, the decision block, and the flow path;

determine a decision for the applicant based on the information associated with the applicant, the data associated with the applicant from at least one data source, the information associated with the plurality of decision rules determined based on the plurality of decision rules in the near-natural language, and the decision flow by applying in accordance with the decision flow an executable version of the information associate with the plurality of decision rules in the near-natural language to the data associated with the applicant from at least one data source; and

provide the decision to the user interface.

34. The system of claim 33, wherein the processor is configured to execute stored instructions to apply in accordance with the plurality of decision rules in the near-natural language to the data associated with the applicant from at least one data source to generate a decision for the applicant by:

determining a series of execution steps from the decision rule associated with the plurality of decision rules;

in accordance with the series of execution steps, generating at least one attribute representing a statistical aggregation of at least one of (i) the data associated with the applicant from at least one data source;

or (ii) the information associated with the applicant; and

applying the information associated with the plurality of decision rules on the at least one attribute to generate the decision, the decision comprising one of;

denial of a credit line;

granting an approval of a credit line;

denial of a loan;

granting approval of a loan;

or

approval for receiving an offer of credit.

35. The system of claim 33, wherein the processor is adapted to configure the user interface to allow the user to define the plurality of decision rules in the near-natural language by:

displaying a plurality of elements for constructing at least one of the plurality of decision rules, the plurality of elements comprising decision tables, exclusionary rules, rule flows, template libraries, and a deployer;

receiving a selection by the user, the selection comprising at least part of the plurality of elements;

receiving an attribute or a criteria associated with the selection by the user; and

constructing a graphical representation of the at least one of the plurality of decision rules using the selection by the user and the attribute or the criteria.

36. The system of claim 33, wherein the processor is configured to execute stored instructions to compare the information associated with the applicant with at least some of the data associated with the applicant from the at least one data source to determine if the information associated with the applicant is valid.