Computer-implemented systems and methods for loan evaluation using a credit assessment framework

• US 8,521,631 B2
• Filed: 05/29/2009
• Issued: 08/27/2013
• Est. Priority Date: 05/29/2008
• Status: Active Grant

• Current Assignee: SAS Institute Incorporated
• Original Assignee: SAS Institute Incorporated
• Inventors: Abrahams, Clark Richard, Zhang, Mingyuan
• Primary Examiner(s): KANERVO, VIRPI H
• Application Number:
  US12/474,941
• Publication Number:
  US 20090299911A1
• Time in Patent Office: 1,551 Days
• Field of Search: None
• US Class Current: 705/36.R
• 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
• CPC Class Codes: G06Q 40/06 Asset management; Financial planning or analysis
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

Systems and methods are provided for evaluating loan applications. A computer environment can include a loan evaluation system which operates on a processor-based system and which evaluates loan applications. A credit assessment framework is also provided for operating on the processor-based system and has a data connection to the loan evaluation system. The credit assessment framework generates a categorization of credit risk for each of the loan applications to be evaluated.

Claims

1. A computer-implemented method of evaluating a loan application, comprising:

generating, using one or more data processors, a borrower contour map, wherein the borrow contour map identifies a borrower score for each of a plurality of different combinations of borrower attributes, and wherein the borrower attributes include a character attribute, a capacity attribute, and a capital attribute;

generating, using the one or more data processors, a transaction contour map, wherein the transaction contour map identifies a transaction score for each of a plurality of different combinations of transaction attributes, and wherein the transaction attributes include the borrower attributes, a collateral attribute, and a conditions attribute;

performing, using the one or more data processors, a simulation corresponding to future economic conditions, wherein the simulation predicts performance of loans, and wherein the loans are associated with different borrower score-transaction score combinations;

generating, using the one or more data processors, a loan decision model using the predicted performances, wherein the loan decision model associates an action with each borrower score-transaction score combination;

receiving, using the one or more data processors, a loan application that includes one or more ratings for the borrower attributes and the transaction attributes;

assigning, using the one or more data processors, an application borrower score to the loan application using the borrower contour map and the borrower attribute ratings;

assigning, using the one or more data processors, an application transaction score to the loan application using the transaction contour map and the transaction attribute ratings; and

determining, using the one or more data processors, an action for the loan application using the loan decision model, the application borrower score, and the application transaction score.

2. The method of claim 1, wherein the borrower score and the transaction score are based on a scale of 1-10.

3. The method of claim 1, wherein non-credit data is used in the simulation corresponding to future economic conditions.

4. The method of claim 1, wherein the borrower attributes include one or more primary underwriting factors from a set of primary underwriting factors.

5. The method of claim 4, wherein the transaction attributes include the set of primary underwriting factors.

6. The method of claim 1, wherein the actions include approval, denial, price, and terms.

7. The method of claim 6, wherein multiple loans of a loan portfolio are evaluated.

8. The method of claim 1, wherein the character attribute is based upon a payment history, a savings history, insurance coverage, an education level, or a stability measure.

9. The method of claim 1, wherein the capacity attribute is based upon income, debt obligations, cash obligations, living expenses, or number of dependents.

10. The method of claim 1, wherein the capital attribute is based upon net worth, amount of assets, or liquidity of assets.

11. The method of claim 1, wherein the loan decision model is validated by repeating the simulation.

12. The method of claim 1, further comprising:

generating a graphical interface for evaluating the loan application.

13. The method of claim 1, wherein the determined action is performed for the loan application.

14. A computer-implemented system for evaluating a loan application, comprising:

one or more data processors;

one or more computer-readable storage mediums containing instructions configured to cause the one or more processors to perform operations including;

generating a borrower contour map, wherein the borrow contour map identifies a borrower score for each of a plurality of different combinations of borrower attributes, and wherein the borrower attributes include a character attribute, a capacity attribute, and a capital attribute;

generating a transaction contour map, wherein the transaction contour map identifies a transaction score for each of a plurality of different combinations of transaction attributes, and wherein the transaction attributes include the borrower attributes, a collateral attribute, and a conditions attribute;

performing a simulation corresponding to future economic conditions, wherein the simulation predicts performance of loans, and wherein the loans are associated with different borrower score-transaction score combinations;

generating a loan decision model using the predicted performances, wherein the loan decision model associates an action with each borrower score-transaction score combination;

receiving a loan application that includes one or more ratings for the borrower attributes and the transaction attributes;

assigning an application borrower score to the loan application using the borrower contour map and the borrower attribute ratings;

assigning an application transaction score to the loan application using the transaction contour map and the transaction attribute ratings; and

determining an action for the loan application using the loan decision model, the application borrower score, and the application transaction score.

15. The system of claim 14, wherein the borrower score and the transaction score are based on a scale of 1-10.

16. The system of claim 14, wherein performing the simulation includes using non-credit data corresponding to future economic conditions in the simulation.

17. The system of claim 14, wherein the borrower attributes include one or more primary underwriting factors from a set of primary underwriting factors.

18. The system of claim 17, wherein the transaction attributes include the set of primary underwriting factors.

19. The system of claim 14, wherein the actions include approval, denial, price, and terms.

20. The system of claim 19, wherein multiple loans of a loan portfolio are evaluated.

21. The system of claim 14, wherein the character attribute is based upon a payment history, a savings history, insurance coverage, an education level, or a stability measure.

22. The system of claim 14, wherein the capacity attribute is based upon income, debt obligations, cash obligations, living expenses, or number of dependents.

23. The system of claim 14, wherein the capital attribute is based upon net worth, amount of assets, or liquidity of assets.

24. The system of claim 14, wherein the operations further include validating the loan decision model by repeating the simulation.

25. The system of claim 14, wherein the operations further include:

generating a graphical interface for evaluating the loan application.

26. The system of claim 14, wherein the determined action is performed for the loan application.

27. A computer-program product for evaluating a loan application, the computer-program product tangibly embodied in a machine-readable, non-transitory storage medium, the storage medium including instructions executable to cause a data processing apparatus to:

generate a borrower contour map, wherein the borrow contour map identifies a borrower score for each of a plurality of different combinations of borrower attributes, and wherein the borrower attributes include a character attribute, a capacity attribute, and a capital attribute;

generate a transaction contour map, wherein the transaction contour map identifies a transaction score for each of a plurality of different combinations of transaction attributes, and wherein the transaction attributes include the borrower attributes, a collateral attribute, and a conditions attribute;

perform a simulation corresponding to future economic conditions, wherein the simulation predicts performance of loans, and wherein the loans are associated with different borrower score-transaction score combinations;

generate a loan decision model using the predicted performances, wherein the loan decision model associates an action with each borrower score-transaction score combination;

receive a loan application that includes one or more ratings for the borrower attributes and the transaction attributes;

assign an application borrower score to the loan application using the borrower contour map and the borrower attribute ratings;

assign an application transaction score to the loan application using the transaction contour map and the transaction attribute ratings; and

determine an action for the loan application using the loan decision model, the application borrower score, and the application transaction score.

28. The computer-program product of claim 27, wherein the borrower score and the transaction score are based on a scale of 1-10.

29. The computer-program product of claim 27, wherein non-credit data is used in the simulation corresponding to future economic conditions.

30. The computer-program product of claim 27, wherein the borrower attributes include one or more primary underwriting factors from a set of primary underwriting factors.

31. The computer-program product of claim 30, wherein the transaction attributes include the set of primary underwriting factors.

32. The computer-program product of claim 27, wherein the actions include approval, denial, price, and terms.

33. The computer-program product of claim 32, wherein multiple loans of a loan portfolio are evaluated.

34. The computer-program product of claim 27, wherein the character attribute is based upon a payment history, a savings history, insurance coverage, an education level, or a stability measure.

35. The computer-program product of claim 27, wherein the capacity attribute is based upon income, debt obligations, cash obligations, living expenses, or number of dependents.

36. The computer-program product of claim 27, wherein the capital attribute is based upon net worth, amount of assets, or liquidity of assets.

37. The computer-program product of claim 27, wherein the instructions are further executable to cause the data processing apparatus to validate the loan decision model by repeating the simulation.

38. The computer-program product of claim 27, wherein the instructions are further executable to cause the data processing apparatus to:

generate a graphical interface for evaluating the loan application.

39. The computer-program product of claim 27, wherein the determined action is performed for the loan application.