Method and apparatus for predicting outcomes of a home equity line of credit
View Patent ↗A method and apparatus are described where account information is used to predict possible outcomes of a HELOC. To predict the possible outcomes, HELOC account state transition probabilities are modeled. The transition probabilities, determined by historic data regression analysis, provide the framework for a Monte Carlo simulation. The simulation is seeded with HELOC account information. A calculation engine takes the account information and simulates an elapse of time using a random number generator and the state transition probabilities. The simulation results in updated account information predicting a possible outcome over the elapsed time interval. The updated account information in turn may be used by the calculation engine to simulate the next elapse of time. This method may be iteratively repeated with the account information propagated forward until the end of the prediction period is reached.
1. A machine-readable medium comprising instructions for predicting outcomes of a home equity line of credit loan, wherein the instructions upon execution cause a machine to:
receive a plurality of account characteristics for a home equity line of credit loan;
generate an initial account state vector from the plurality of account characteristics;
provide a plurality of account states, at least one account state representing a mutually exclusive duration of delinquency;
generate a random number;
update the initial account state vector by propagating a state vector forward to one of the plurality of account states using a statistical transition model and the random number;
predict draw or payment events using the statistical transition model; and
generate a probability distribution using the statistical transition model, the probability distribution related to at least one of a risk of default, a risk of delinquency, or a risk of prepayment.
2. The machine-readable medium of claim 1 wherein the plurality of account characteristics are selected from a group consisting of a location of a home, a loan origination date, a property value, an occupancy type, a junior ratio, a utilization at origination, a balance at origination, a term, a back end ratio, a prediction start date, an index rate, a margin, an interest rate, a home price index, and combinations thereof.
3. The machine-readable medium of claim 1 wherein the initial account state vector includes information that is used to determine at least one probability for each state transition.
4. The machine-readable medium of claim 1 further comprising instructions that upon execution cause a machine to receive a simulation parameter, wherein the simulation parameter is selected from a group consisting of a loan prediction period, a prediction interval, a number of Monte Carlo trials, and combinations thereof.
5. The machine-readable medium of claim 4 further comprising instructions that upon execution cause a machine to store an account state vector, the number of Monte Carlo trials, and the prediction interval.
6. The machine-readable medium of claim 5 further comprising instructions that upon execution cause a machine to store the initial account state vector as the account state vector, a 1 for the number of Monte Carlo trials, and a 0 for the prediction interval if no account state vector, trial number and prediction interval exist.
7. The machine-readable medium of claim 1 wherein the statistical transition model includes equations and coefficients to determine transition probabilities based on the information in the account state vector.
8. A computer-based method for predicting outcomes of a home equity line of credit loan comprising:
receiving, at a computer, a plurality of account characteristics for a home equity line of credit loan;
generating, by the computer, an initial account state vector from the plurality of account characteristics;
providing, at the computer, a plurality of account states, at least one account state representing a mutually exclusive duration of delinquency;
updating, at the computer, the initial account state vector by propagating a state vector forward to one of the plurality of account states using a statistical transition model and a random number that simulates the effect of a lapse of time on the initial account state vector;
predicting, by the computer, draw or payment events using the statistical transition model; and
generating, by the computer, a probability distribution using the statistical transition model, the probability distribution related to at least one of a risk of default, a risk of delinquency, or a risk of prepayment.
9. The method of claim 8 wherein the plurality of account characteristics are selected from a group consisting of a location of a home, a loan origination date, a property value, an occupancy type, a junior ratio, a utilization at origination, a balance at origination, a term, a back end ratio, a prediction start date, an index rate, a margin, an interest rate, a home price index, and combinations thereof.
10. The method of claim 8 wherein the initial account state vector includes information that is used to determine at least one probability for each state transition.
11. The method of claim 8 further comprising receiving, at the computer, a simulation parameter, wherein the simulation parameter is selected from a group consisting of a loan prediction period, a prediction interval, a number of Monte Carlo trials, and combinations thereof.
12. The method of claim 11 further comprising storing, at the computer, an account state vector, the number of Monte Carlo trials, and the prediction interval.
13. The method of claim 12 further comprising storing, at the computer, the initial account state vector as the account state vector, a 1 for the number of Monte Carlo trials, and a 0 for the prediction interval if no account state vector, trial number and prediction interval exist.
14. The method of claim 8 wherein the statistical transition model includes equations and coefficients to determine transition probabilities based on the information in the account state vector.
15. The machine-readable medium of claim 1 wherein the propagation of the state vector forward to one of the plurality of account states represents an event selected from a group of possible events, wherein one of the possible events represents a draw on a home equity line of credit.