Systems and methods for determining the likelihood that a loan closes

• US 8,239,318 B1
• Filed: 09/13/2011
• Issued: 08/07/2012
• Est. Priority Date: 11/04/2003
• Status: Active Grant

• Current Assignee: Freddie Mac
• Original Assignee: Freddie Mac
• Inventors: Bradley, Michael G., Gordon, J. Douglas, Klena, Matthew J., Sims, Pamela W.
• Primary Examiner(s): Robinson, Kito R
• Application Number:
  US13/231,395
• Time in Patent Office: 329 Days
• Field of Search: 705/38, 705/35
• US Class Current: 705/38
• 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

Abstract

Systems and methods are provided for determining an indication that an application for a mortgage loan to secure a property may result in closing of the loan transaction. In one embodiment, a method includes receiving application information, such that the application information includes at least borrower information, property information, and a first interest rate; receiving home value information, such that the home value information represents an estimated value of the property; receiving a second interest rate; and determining the indication based on the received application information, received home value information, and received second interest rate, such that the indication represents a likelihood that the mortgage loan may result in closing.

Claims

1. A computer-implemented method for determining an order for performing appraisals on one or more properties based on scores, wherein each of the scores indicates whether a mortgage loan application is likely to result in a closing, comprising:

receiving, by a data processor from one or more databases, a first score for a first property;

receiving, by the data processor from one or more databases, a second score for a second property; and

comparing, by the data processor, the first score and the second score to determine an order in which to perform a first appraisal of the first property and a second appraisal of the second property,

the first appraisal of the first property being ordered before the second appraisal of the second property, when the first score indicates a greater likelihood of closing than the second score.

2. The method of claim 1, wherein determining an order comprises:

prioritizing the first appraisal before the second appraisal based on the first score.

3. The method of claim 1, further including:

receiving a date corresponding to when a mortgage loan application for the first property may be closed with a first interest rate; and

receiving a date corresponding to when a mortgage loan application for the second property may be closed with a second interest rate.

4. The method of claim 1, wherein the first score is based, at least in part, on employment information of an applicant associated with a mortgage loan application for the first property.

5. The method of claim 1, wherein the first score is based, at least in part, on financial information of an applicant associated with a mortgage loan application for the first property.

6. The method of claim 1, wherein the first score is based, at least in part, on transaction metrics associated with a mortgage loan application for the first property.

7. The method of claim 1, further comprising applying a score model, wherein the first score and the second score are produced from the score model.

11. The method of claim 7, further comprising periodically applying the score model and producing updated values for the first score and the second score.

12. The method of claim 7, wherein the score model comprises a plurality of adjustable coefficients.

13. The method of claim 12, further comprising adjusting a coefficient using a logistic regression technique.

8. A non-transitory computer-executable program tangibly embodied on a computer readable medium, said program performing a method comprising:

receiving a first score for a first loan;

receiving a second score for a second loan; and

comparing the first score with the second score to determine an order in which to perform a first appraisal for a first property associated with the first loan and a second appraisal for a second property associated with the second loan,

the first appraisal being ordered before the second appraisal when the first score indicates a greater likelihood of the loan closing than the second score.

9. The non-transitory computer-executable program tangibly embodied on a computer-readable medium of claim 8, wherein the program determines the order by prioritizing the first appraisal before the second appraisal based on the first score.

10. The non-transitory computer-executable program tangibly embodied on a computer-readable medium of claim 8, the program performing the method which further includes:

receiving a date corresponding to when a mortgage loan application for the first property may be closed with a first interest rate; and

receiving a date corresponding to when a mortgage loan application for the second property may be closed with a second interest rate.

14. The non-transitory computer-executable program tangibly embodied on a computer-readable medium of claim 8, wherein the first score is based, at least in part, on employment information of an applicant associated with a mortgage loan application for the first property.

15. The non-transitory computer-executable program tangibly embodied on a computer-readable medium of claim 8, wherein the first score is based, at least in part, on financial information of an applicant associated with a mortgage loan application for the first property.

16. The non-transitory computer-executable program tangibly embodied on a computer-readable medium of claim 8, wherein the first score is based, at least in part, on transaction metrics associated with a mortgage loan application for the first property.

17. The non-transitory computer-executable program tangibly embodied on a computer-readable medium of claim 8, the program performing the method which further includes applying a score model, wherein the first score and the second score are produced from the score model.

18. The non-transitory computer-executable program tangibly embodied on a computer-readable medium of claim 17, the program performing the method which further includes periodically applying the score model and producing updated values for the first score and the second score.

19. The non-transitory computer-executable program tangibly embodied on a computer-readable medium of claim 17, wherein the score model comprises a plurality of adjustable coefficients.

20. The non-transitory computer-executable program tangibly embodied on a computer-readable medium of claim 19, the program performing the method which further includes adjusting a coefficient using a logistic regression technique.