Systems and methods for performing scoring optimization

• US 7,925,578 B1
• Filed: 08/26/2005
• Issued: 04/12/2011
• Est. Priority Date: 08/26/2005
• Status: Active Grant

• Current Assignee: JP Morgan Chase Bank, N.A. (JP Morgan Chase & Co)
• Original Assignee: JP Morgan Chase Bank, N.A. (JP Morgan Chase & Co)
• Inventors: Song, Xiaolan, Dong, Xin, Wang, Lihua, Fei, Huchen, Hong, Xiao
• Primary Examiner(s): Kramer; James A
• Assistant Examiner(s): Vezeris; James A
• Application Number:
  US11/211,728
• Time in Patent Office: 2,055 Days
• Field of Search: 705/35, 705/38
• 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

Abstract

Systems and methods relate to generating a unified determination based on a subdetermination, and in particular, generating a unified score based on respective scores. For example, the invention provides a method for generating a unified determination based on subdeterminations, the method including generating a first subdetermination based on first criteria; generating a second subdetermination based on second criteria; and generating a unified determination based on the first subdetermination and the second subdetermination. The generation of the unified determination includes (a) assigning, using iterative processing, an assigned weighting respectively to the first determination and second determination; (b) determining if the assigned weighting satisfies at least one constraint; (c) comparing the assigned weighting to an optimized weighting, which was previously determined, to determine if the assigned weighting is improved over the optimized weighting; and (d) if the assigned weighting is improved, then assigning the assigned weighting to be the optimized weighting.

Claims

1. A method for generating a unified determination based on subdeterminations, the method implemented on a processing machine, comprising a memory and process, the method including:

generating a first subdetermination based on first criteria, using the processing machine, wherein the first subdetermination is a front end risk score;

generating a second subdetermination based on second criteria, using the processing machine, wherein the second subdetermination is a back end risk score;

wherein the front end risk score determines if an individual is to be mailed an offer for a financial product; and

the back end risk score determines if the individual, who is a respondent to the offer, is to be extended the financial product;

generating a unified determination, using the processing machine, based on the first subdetermination and the second subdetermination, including;

assigning, using iterative processing, for each respective iteration, an assigned weighting factored into a relationship in conjunction with the first subdetermination and second subdetermination;

determining if the assigned weighting, as factored into the relationship, satisfies at least one constraint imposed on the relationship;

comparing the assigned weighting, as factored into a further relationship, to an optimized weighting, as factored into the further relationship, which was previously determined, to determine if the assigned weighting is improved over the optimized weighting; and

if the assigned weighting is improved, then assigning the assigned weighting to be the optimized weighting, whereby the further relationship is further maximized and an improved optimized weighting is identified for use in the unified determination to determine risk associated with an individual.

2. The method of claim 1, wherein the financial product is a credit card.

3. The method of claim 1, further including:

Inputting information from a credit bureau entity; and

Generating the first score and the second score based on the information input from the credit bureau entity.

4. The method of claim 3, including securing information from an applicant for a credit card;

and

using the information from the applicant for a credit card to generate the second score.

5. The method of claim 1, wherein the determining if the assigned weighting satisfies at least one constraint is performed using a first relationship including parameters, the parameters including the first subdetermination, the second subdetermination, the assigned weighting and a first objective parameter, and comparing a result of the first relationship with a first constraint value.

6. The method of claim 5, wherein the determining if the assigned weighting satisfies at least one constraint is performed using a second relationship including parameters, the parameters including the first subdetermination, the second subdetermination, the assigned weighting and a second objective parameter, and comparing a result of the second relationship with a second constraint value.

7. The method of claim 6, wherein the result of the first relationship and the result of the second relationship is computed using a Kolmogorov-Smirnov statistic.

8. The method of claim 1, wherein comparing the assigned weighting to an optimized weighting to determine if the assigned weighting is improved over the optimized weighting includes:

using a first relationship including first parameters to generate a first result, the first parameters including the first subdetermination, the second subdetermination, the assigned weighting and a first objective parameter; and

using a second relationship including second parameters to generate a second result, the second parameters including the first subdetermination, the second subdetermination, the optimized weighting and the first objective parameter, and

comparing the first result to the second result.

9. The method of claim 8, wherein the first result and the second result are computed using a Kolmogorov-Smirnov statistic.

10. The method of claim 8, further including using a second objective parameter in determining the first result and the second result.

11. The method of claim 1, wherein the iterative processing is effected using a progressing value, the progressing value being advanced after (a) the determining if the assigned weighting satisfies at least one constraint, and (b) comparing the assigned weighting to an optimized weighting.

12. The method of claim 11, wherein the progressing value is advanced until the progressing value attains a threshold value, which marks the final iteration.

13. The method of claim 11, wherein the assigning, using iterative processing, the assigned weighting respectively to the first determination and second determination includes utilizing a random number generator to assign the weighting.

14. The method of claim 1, wherein the determining if the assigned weighting satisfies at least one constraint is performed, and if the at least one constraint is satisfied, then comparing the assigned weighting to an optimized weighting, which was previously determined, to determine if the assigned weighting is improved over the optimized weighting.

15. A system that generates a unified determination based on subdeterminations, the system including:

a memory;

a processor;

a first score processor generating a first subdetermination based on first criteria, wherein the first subdetermination is a front end risk score;

a second score processor generating a second subdetermination based on second criteria, wherein the second subdetermination is a back end risk score;

wherein the front end risk score determines if an individual is to be mailed an offer for a financial product; and

the back end risk score determines if the individual, who is a respondent to the offer, is to be extended the financial product;

a combination score processor generating a unified determination based on the first subdetermination and the second subdetermination, the combination score processor including;

an iteration control portion assigning, using iterative processing, an assigned weighting that is factored into a relationship in conjunction with the first subdetermination and second subdetermination;

a feasibility determination portion determining if the assigned weighting, as factored into the relationship, satisfies at least one constraint imposed on the relationship;

a comparison portion comparing the assigned weighting, as factored into a further relationship, to an optimized weighting, as factored into the further relationship, which was previously determined, to determine if the assigned weighting is improved over the optimized weighting; and

if the assigned weighting is improved, then assigning the assigned weighting to be the optimized weighting, whereby the further relationship is further maximized and an improved optimized weighting is identified for use in the unified determination to determine risk associated with an individual.

16. The system of claim 15, wherein the feasibility determination portion determining if the assigned weighting satisfies at least one constraint is performed using a first relationship including parameters, the parameters including the first subdetermination, the second subdetermination, the assigned weighting and a first objective parameter, and comparing a result of the first relationship with a first constraint value.

17. The system of claim 16, wherein the determining if the assigned weighting satisfies at least one constraint is performed using a second relationship including parameters, the parameters including the first subdetermination, the second subdetermination, the assigned weighting and a second objective parameter, and comparing a result of the second relationship with a second constraint value.

18. The system of claim 15, wherein the comparison portion comparing the assigned weighting to an optimized weighting to determine if the assigned weighting is improved over the optimized weighting includes:

using a first relationship including first parameters to generate a first result, the first parameters including the first subdetermination, the second subdetermination, the assigned weighting and a first objective parameter; and

using a second relationship including second parameters to generate a second result, the second parameters including the first subdetermination, the second subdetermination, the optimized weighting and the first objective parameter, and

comparing the first result to the second result.

19. A computer readable medium, embodying program instructions executable by a machine to perform method steps, that generate a unified determination based on subdeterminations, said method steps comprising:

generating, by a first portion, a first subdetermination based on first criteria, wherein the first subdetermination is a front end risk score;

generating, by a second portion, a second subdetermination based on second criteria, wherein the second subdetermination is a back end risk score;

wherein the front end risk score determines if an individual is to be mailed an offer for a financial product; and

the back end risk score determines if the individual, who is a respondent to the offer, is to be extended the financial product;

generating, by a third portion, a unified determination, based on the first subdetermination and the second subdetermination, including;

assigning, by an iteration control portion, using iterative processing, an assigned weighting factored into a relationship in conjunction with the first subdetermination and second subdetermination;

determining, by a feasibility determination portion, if the assigned weighting, as factored into the relationship, satisfies at least one constraint imposed on the relationship;

comparing, by a comparison portion, the assigned weighting, as factored into a further relationship, to an optimized weighting, as factored into the further relationship, which was previously determined, to determine if the assigned weighting is improved over the optimized weighting; and

if the assigned weighting is improved, then the comparison portion assigning the assigned weighting to be the optimized weighting, whereby the further relationship is further maximized and an improved optimized weighting is identified for use in the unified determination to determine risk associated with an individual.