Apparatus and method for modeling the risk of loans in a financial portfolio

• US 6,078,903 A
• Filed: 02/12/1998
• Issued: 06/20/2000
• Est. Priority Date: 02/12/1998
• Status: Expired due to Fees

• Current Assignee: KMV Development LP
• Original Assignee: KMV Development LP
• Inventors: Kealhofer, Stephen
• Primary Examiner(s): MacDonald, Allen R.
• Assistant Examiner(s): MEINECKE DIAZ, SUSANNA M
• Application Number:
  US09/022,769
• Time in Patent Office: 859 Days
• Field of Search: 705/35, 705/36, 705/38
• US Class Current: 705/36.00R
• 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

A method executed by a computer under the control of a program includes the steps of storing financial portfolio data in the computer. The financial portfolio data includes data on a loan representing a liability of a specified entity. A horizon date is selected for the loan. A distribution function is then designated to characterize the probability of different market values for the specified entity at the horizon date. A horizon default point threshold is then adjusted at the horizon date until the area bound by the distribution function, the horizon date, and the horizon default point threshold is equal to a horizon date cumulative default rate for the specified entity. A maturity date is also defined for the loan. A final default point threshold is then determined at the maturity date so that an expected default rate from the horizon date to the maturity date is equal to a maturity date cumulative default rate, less the horizon date cumulative default rate. Once the horizon default point threshold and the maturity default point threshold are defined in this manner, a number of input parameters can be derived for further financial portfolio analyses. The portfolio analyses include loan value correlations between affiliated entities.

Claims

1. A method executed by a computer under the control of a program, said method comprising the steps of:

storing financial portfolio data in said computer, said financial portfolio data including data on a loan representing a liability for a specified entity of a financial portfolio;

selecting a horizon date for said loan;

designating a distribution function to characterize a probability of different market values for said specified entity at said horizon date;

adjusting a horizon default point threshold at said horizon date until an area bound by said distribution function, said horizon date, and said horizon default point threshold is equal to a horizon date cumulative default rate for said specified entity, so as to characterize risk associated with said loan; and

generating a report and graph characterizing risk associated with said loan.

2. The method of claim 1 further comprising the steps of:

defining a maturity date for said loan;

designating a second distribution function to characterize a probability of different market values for said entity at said maturity date;

determining a default rate from said horizon date to said maturity date for each market value at said horizon date, given a maturity default point threshold; and

determining said maturity default point threshold so that an expected default rate from said horizon date to said maturity date is equal to a maturity date cumulative default rate, less said horizon date cumulative default rate.

3. The method of claim 2 further comprising the step of determining a loan value distribution function from said maturity default point threshold and said distribution function of said horizon date entity values.

4. The method of claim 2 further comprising the steps of:

defining a standard deviation associated with said distribution function;

designating a number of standard deviation increments between said horizon default point threshold and a horizon date entity value associated with said specified entity; and

determining the value of said loan from said number of said standard deviation increments.

5. The method of claim 3 further comprising the step of establishing a horizon expected value for said loan and a variance for said loan in reliance upon said loan value distribution function.

6. The method of claim 5 further comprising the step of combining a given initial value for said loan with said horizon expected value for said loan and said variance for said loan to determine values for an expected return and return variance of said loan.

7. The method of claim 1 further comprising the step of correlating said loan of said specified entity with a second loan of a second specified entity of said financial portfolio by determining an entity correlation value, and by determining default rate values appropriate to an entity relationship between said specified entity and said second specified entity.

8. The method of claim 7 further comprising the step of selectively designating said entity relationship as a dependent subsidiary relationship, a semi-dependent subsidiary relationship, and a guaranteed entity relationship.

9. The method of claim 8 wherein said entity correlation value is determined for said entity relationship;

and said default rate values are determined for said specified entity and said second specified entity of said entity relationship.

10. A method executed by a computer under the control of a program, said method comprising the steps of:

storing financial portfolio data in said computer, said financial portfolio data including data on a first loan of a first specified entity and a second loan of a second specified entity of a financial portfolio;

correlating said first loan and said second loan by determining an entity correlation value, and by determining default rate values appropriate to an entity relationship between said first specified entity and said second specified entity;

selectively designating said entity relationship as a dependent subsidiary relationship, a semi-dependent subsidiary relationship, and a guaranteed entity relationship, so as to characterize risk associated with said first loan and said second loan; and

generating a report and graph characterizing risk associated with said first loan and said second loan.

11. The method of claim 10 wherein said entity correlation value is determined for said entity relationship.

12. The method of claim 11 further comprising the step of determining a default rate based upon said entity relationship.

13. A computer readable memory that can be used to direct a computer to function in a specified manner, comprising:

a first module storing financial portfolio data including data on a loan representing a liability for a specified entity of a financial portfolio;

a second module to select a horizon date for said loan;

a third mobile to designate a distribution function to characterize a probability of different market values for said specified entity at said horizon date; and

a fourth module to adjust a horizon default point threshold at said horizon date until the area bound by said distribution function, said horizon date, and said horizon default point threshold is equal to a horizon date cumulative default rate for said specified entity, so as to characterize risk associated with said loan, said fourth module generating a report and graph characterizing risk associated with said loan.

14. The computer readable memory of claim 13 further comprising:

a fifth module defining a maturity date for an individual financial asset; and

a sixth module to designate a second distribution function to characterize a probability of different market values for said entity at said maturity date, to determine a default rate from said horizon date to said maturity date for each market value at said horizon date, given a maturity default point threshold, and to determine said maturity default point threshold so that an expected default rate from said horizon date to said maturity date is equal to a maturity date cumulative default rate, less said horizon date cumulative default rate.

15. The computer readable memory of claim 14 further comprising a seventh module to determine a loan value distribution function from said maturity default point threshold and said distribution function of said specified entity at said horizon date.

16. The computer readable memory of claim 15 further comprising an eighth module to correlate said loan of said specified entity with a second loan of a second specified entity of said financial portfolio by determining an entity correlation value, and by determining default rate values appropriate to an entity relationship between said specified entity and said second specified entity.

17. The computer readable memory of claim 16 wherein said eighth module selectively characterizes the relationship between said specified entity and said second specified entity as a dependent subsidiary relationship, a semi-dependent subsidiary relationship, or a guaranteed entity relationship.