Method and apparatus for determining loan prepayment scores

• US 6,185,543 B1
• Filed: 05/15/1998
• Issued: 02/06/2001
• Est. Priority Date: 05/15/1998
• Status: Expired due to Term

• Current Assignee: Experian Information Solutions Incorporated (Experian plc)
• Original Assignee: Marketswitch Corp. (Experian plc)
• Inventors: Jones, Charles L. III, Eginton, William A., Fishman, Vladimir, Galperin, Yuri
• Primary Examiner(s): Swann, Tod R.
• Assistant Examiner(s): MEINECKE DIAZ, SUSANNA M
• Application Number:
  US09/078,867
• Time in Patent Office: 998 Days
• Field of Search: 705/38, 705/35, 705/36, 705/7, 705/1
• US Class Current: 705/38
• CPC Class Codes: G06Q 40/03 Credit; Loans; Processing thereof
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

A method and apparatus for determining the prepayment propensity of borrowers. Earlier payment of loans and particularly mortgage loans can lead to losses being suffered by lenders. The present invention analyzes the demographics associated with a particular borrower to determine both the individual and group based prepayment propensity. The history of the borrower, the history of the demographic group to which the borrower belongs, interest rate trends and other factors are then used to calculate a prepayment score that can be used by the lender to determine the propensity of a given borrower to prepay the loan in question. Where prepayment is a significant risk, inducements to the borrower to leave the loan in force can be made or the loan product can be adjusted to reflect the prepayment risk involved. Loan brokers can also be rated based upon the prepayment propensity of those borrowers who are clients of the broker. As with borrowers, a prepayment score can be attributed to a loan broker based upon the prepayment behavior of the brokers clients. This will help lenders assess the success of brokers with whom the lender deals.

Claims

1. A system for determining prepayment scores representative of prepayment propensity of consumers for consumer mortgage loan originations, comprising:

a plurality of loan origination terminals for accepting and transmitting consumer mortgage loan applications;

a network connected to the plurality of loan origination terminals for receiving the transmitted consumer mortgage loan applications;

a communication server connected to the network for receiving the transmitted consumer mortgage loan applications;

an application parser connected to the communications server for receiving the transmitted consumer mortgage loan applications from the communications server and parsing the information into loan information and applicant information;

a prepayment model library database comprising loan prepayment models connected to the application parser for receiving the loan information and fitting the loan information into the loan prepayment models and for transmitting loan prepayment models that match the loan information; and

a prepayment calculation server comprising a prepayment score generation model connected to the prepayment model library database for receiving the loan prepayment models and calculating prepayment scores for each consumer mortgage loan application based upon the loan prepayment model and the prepayment score generation model, the prepayment calculation server is further adapted to transmit the prepayment scores to any one of the plurality of loan origination terminals via the communications server and the network;

where the prepayment score is calculated from the formula;

$\mathrm{Score}=\underset{T}{\sum <br><br>}<br><br>\mathrm{TP}<br><br>\left(T\right)$

where T represents time and P represents prepayment; and

wherein the plurality of loan origination terminals are adapted to use the prepayment scores to adjust terms of the consumer mortgage loans.

2. The system for determining prepayment scores of claim 1, where the prepayment model library database further comprises:

a model training server for creating the loan prepayment models for the prepayment model library database; and

prepayment historical data connected to the model training server, the prepayment historical data further comprises prepayment statistics regarding loans of various types.

3. The system for determining prepayment scores of claim 1, where the prepayment calculation server further comprises an econometric model that generates Low Discrepancy Sequence (LDS)-based scenarios of econometric parameters for input to the prepayment calculation server.

4. The system for determining prepayment scores of claim 1, where total prepayment at time T is calculated from the formula:

$P<br><br>\left(T\right)=\left(1/S\right)<br><br>\underset{s=1}{\overset{S}{\sum <br><br>}}<br><br>P_s<br><br>\left(T\right)$

where S represents the number of scenarios and P represents the prepayment amount for a given scenario.

5. The system for determining prepayment scores of claim 4, where the total prepayment, accumulated by time, in scenario s is calculated from the formula:

$P_s<br><br>\left(T\right)=\underset{i}{\prod <br><br>}<br><br>p_s<br><br>\left(t_i\right)$

where p(t) is a prepayment value.

6. The system for determining prepayment scores of claim 5, where the prepayment value in a given scenario is calculated from the formula:

7. A method for determining prepayment scores representative of prepayment propensity of loan applicants comprising:

collecting loan and applicant information at a loan originator;

transmitting the loan and applicant information over a network;

receiving the loan and applicant information at a service bureau;

the service bureau calculating a prepayment score for each applicant,

where the prepayment score is calculated from the formula;

$\mathrm{Score}=\underset{T}{\sum <br><br>}<br><br>\mathrm{TP}<br><br>\left(T\right)$

where T represents time and P represents prepayment;

the service bureau returning the prepayment scores over the network to the loan originator; and

the loan originator using the prepayment scores to customize loan products for the applicants.

8. The method for determining prepayment scores of claim 7, where calculating a prepayment score for the applicant comprises a parser parsing the information into loan information and applicant information.

9. The method for determining prepayment scores of claim 8, further comprising providing the applicant information to a prepayment model library database and the loan information to a prepayment calculation server.

10. The method for determining prepayment scores of claim 9, further comprising the prepayment model library determining the prepayment model that best applies to the loan information and providing that prepayment model to the prepayment calculation server.

11. The method for determining prepayment scores of claim 10, further comprising the prepayment calculation server receiving a prepayment model and an econometric model, where the prepayment calculation server further calculates a prepayment score for the applicant.

12. The method for determining prepayment scores of claim 11, where the total prepayment at time T is calculated from the formula:

$P<br><br>\left(T\right)=\left(1/S\right)<br><br>\underset{s=1}{\overset{S}{\sum <br><br>}}<br><br>P_s<br><br>\left(T\right)$

where S represents the number of scenarios and P represents the prepayment amount for a given scenario.

13. The method for determining prepayment scores of claim 12, where the total prepayment, accumulated by time, in scenario s is calculated from the formula:

$P_s<br><br>\left(T\right)=\underset{i}{\prod <br><br>}<br><br>p_s<br><br>\left(t_i\right)$

where p(t) is a prepayment value.

14. The method for determining prepayment scores of claim 13, where the prepayment value in a given scenario is calculated from the formula: