# US 2012/0254061 A1 · Loan resolution modeling using discrete event simulation methodology

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2012/0254061 A1
- Document ID: US20120254061A1
- Status: Published application
- Kind: A1
- Application number: 13/115,710
- Filed: 2011-05-25
- Published: 2012-10-04
- Earliest claimed: 2011-03-30
- Assignees: Bank of America Corporation
- Inventors: Yang Liu; Willys Otieno; Steven W. Lindsey; Minzhe Wu
- Web page: https://patentgrep.com/patent/US20120254061A1

## CPC

- G06Q 40/02: Banking, e.g. interest calculation or account maintenance (credit or loans G06Q40/03)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

Systems, methods, and computer program products are provided for customer loan lifecycle modeling using discrete event simulation methodology. Discrete Event Simulation (DES) allows for modeling to occur at the customer and/or account level, such that the process captures customer-specific or loan-specific attributes/risk factors, such as, but not limited to, credit score(s), House Price Index (HPI), loan product type, unemployment rates, interest rates and the like. Such modeling takes into the account that loan events occur at random paces and are typically dependent on ancillary factors, such as, availability of financial resources, market demand, customer attributes and the like, which all tend to be stochastic by nature.

## Claims

### Claim 1

A method for providing loan resolution modeling, the method comprising:
identifying, via a computing device processor, a current loan state for one or more financial institution loan accounts; and
predicting, via a computing device processor, a future loan state for each of the one or more financial institution loan accounts based on the current loan state, wherein the future loan state is for a predetermined time interval and wherein Discrete Event Simulation processing is implemented to determine the future loan state.

### Claim 2 (depends on 1)

The method of claim 1, wherein predicting the future loan state further comprises predicting, via the computing device processor, the future loan state based on historical aggregated loan account data.

### Claim 3 (depends on 1)

The method of claim 1, wherein predicting the future loan state further comprises predicting, via the computing device processor, the future loan state based on one or more predictive dynamic loan variables.

### Claim 4 (depends on 3)

The method of claim 3, wherein predicting the future loan state further comprises predicting, via the computing device processor, the future loan state based on the one or more predictive dynamic loan variables, wherein the predictive dynamic loan variables include one or more of interest rates, unemployment rates, market-to-market combined loan-to-value, loan age, home price index, home price momentum or payment shock.

### Claim 5 (depends on 1)

The method of claim 1, wherein predicting the future loan state further comprises predicting, via the computing device processor, the future loan state based on one or more predictive static loan variables.

### Claim 6 (depends on 5)

The method of claim 5, wherein predicting the future loan state further comprises predicting, via the computing device processor, the future loan state based on the one or more predictive static loan variables, wherein the predictive static loan variables include credit scores, origination loan-to-value, origination combined loan-to-value, loan age, household income, occupancy status, loan product type, loan purpose, loan amount, amortization term, property type or number of borrowers.

### Claim 7 (depends on 1)

The method of claim 1, wherein identifying the current loan state further comprises identifying, via the computing device processor, the current loan state based on currency or delinquency of the one or more loan accounts.

### Claim 8 (depends on 1)

The method of claim 1, further comprising identifying, via a computing device processor, for each of the one or more loan accounts, a current loan state grouping from amongst a plurality of current loan state groupings.

### Claim 9 (depends on 8)

The method of claim 8, wherein identifying the current loan state grouping further comprises identifying, via a computing device processor, for each of the one or more loan accounts, the current loan state grouping from amongst the plurality of current loan state groupings, wherein the plurality of current loan state groupings include a first grouping that includes loan accounts currently less than ninety days delinquent, a second grouping that includes loan accounts currently ninety to one hundred and seventy-nine days delinquent and a third grouping that includes loan accounts currently greater than or equal to one hundred and eighty days delinquent.

### Claim 10 (depends on 8)

The method of claim 8, wherein predicting the future loan state further comprises predicting, via the computing device processor, the future loan state for each of the one or more loan accounts based on the identified current loan state grouping.

### Claim 11 (depends on 1)

The method of claim 1, wherein predicting the future loan state further comprises predicting, via the computing device processor, the future loan state for each of the one or more loan accounts based on historical loan account-specific data.

### Claim 12 (depends on 1)

The method of claim 1, wherein identifying the current loan state further comprises identifying, via the computing device processor, a plurality of existing loan accounts and a plurality of planned new loan accounts opening during an ensuing time period defined by the predetermined time interval.

### Claim 13

An apparatus for modeling loan resolution, the apparatus comprising:
a computing platform including a processor and a memory in communication with the processor;
a loan resolution application stored in the memory, executable by the processor and configured to identify a current loan state for each of one or more financial institution loan accounts and predict a future loan state for each of the one or more financial institution loan accounts based on the current loan state, wherein the future loan state is for a predetermined time interval and wherein Discrete Event Simulation processing is implemented to determine the future loan state.

### Claim 14 (depends on 13)

The apparatus of claim 13, wherein the loan resolution application is further configured to predict the future loan state based on historical aggregated loan account data.

### Claim 15 (depends on 13)

The apparatus of claim 13, wherein the loan resolution application is further configured to predict the future loan state based on one or more predictive dynamic loan variables.

### Claim 16 (depends on 15)

The apparatus of claim 15, wherein the loan resolution application is further configured to predict the future loan state based on the one or more predictive dynamic loan variables, wherein the predictive dynamic loan variables include one or more of interest rates, unemployment rates, market-to-market combined loan-to-value, loan age, home price index, home price momentum or payment shock.

### Claim 17 (depends on 13)

The apparatus of claim 13, wherein the loan resolution application is further configured to predict the future loan state based on one or more predictive static loan variables.

### Claim 18 (depends on 17)

The apparatus of claim 17, wherein the loan resolution application is further configured to predict the future loan state based on the one or more predictive static loan variables, wherein the predictive static loan variables include credit scores, origination loan-to-value, origination combined loan-to-value, loan age, household income, occupancy status, loan product type, loan purpose, loan amount, amortization term, property type or number of borrowers.

### Claim 19 (depends on 13)

The apparatus of claim 13, wherein the loan resolution application is further configured to identify the current loan state based on currency or delinquency of the one or more loan accounts.

### Claim 20 (depends on 13)

The apparatus of claim 13, wherein the loan resolution application includes an initialization module configured to identity the current loan state for each of the one or more loans based on loan inventory data and planned new loan accounts.

### Claim 21 (depends on 13)

The apparatus of claim 13, wherein the loan resolution application is further configured to identify, for each of the one or more loan accounts, a current loan state grouping from amongst a plurality of current loan state groupings.

### Claim 22 (depends on 21)

The apparatus of claim 21, wherein the loan resolution application further comprises a loan migration module configured to predict the future loan state of loan accounts currently residing in a loan state grouping defined by loan accounts currently less than ninety (90) delinquent.

### Claim 23 (depends on 21)

The apparatus of claim 21, wherein the loan resolution application further comprises a loan weave module configured to predict the future loan state of loan accounts currently residing in a loan state grouping defined by loan accounts currently ninety (90) to one-hundred and seventy-nine (179) days delinquent.

### Claim 24 (depends on 21)

The apparatus of claim 21, wherein the loan resolution application further comprises a loan resolution module configured to predict the future loan state of loan accounts currently residing in a loan state grouping defined by loan accounts greater than or equal to one-hundred and eighty (180) days delinquent.

### Claim 25 (depends on 13)

The apparatus of claim 13, wherein the loan resolution application is further configured to predict the future loan state for each of the one or more loan accounts based on historical loan account-specific data.

### Claim 26

A computer program product including a non-transitory computer-readable medium, the medium comprising:
a first set of codes for causing a computer to identify a current loan state for one or more financial institution loan accounts; and
a second set of codes for causing a computer to predict a future loan state for each of the one or more financial institution loan accounts based on the current loan state, wherein the future loan state is for a predetermined time interval and wherein Discrete Event Simulation processing is implemented to determine the future loan state.

### Claim 27 (depends on 26)

The computer program product of claim 26, wherein the second set of codes is further configured to cause the computer to predict the future loan state based on historical aggregated loan account data.

### Claim 28 (depends on 26)

The computer program product of claim 26, wherein the second set of codes is further configured to cause the computer to predict the future loan state based on one or more predictive dynamic loan variables.

### Claim 29 (depends on 28)

The computer program product of claim 28, wherein the second set of codes is further configured to cause the computer to predict the future loan state based on the one or more predictive dynamic loan variables, wherein the predictive dynamic loan variables include one or more of interest rates, unemployment rates, market-to-market combined loan-to-value, loan age, home price index, home price momentum or payment shock.

### Claim 30 (depends on 26)

The computer program product of claim 26, wherein the second set of codes is further configured to cause the computer to predict the future loan state based on one or more predictive static loan variables.

### Claim 31 (depends on 30)

The computer program product of claim 30, wherein the second set of codes is further configured to cause the computer to predict the future loan state based on the one or more predictive static loan variables, wherein the predictive static loan variables include credit scores, origination loan-to-value, origination combined loan-to-value, loan age, household income, occupancy status, loan product type, loan purpose, loan amount, amortization term, property type or number of borrowers.

### Claim 32 (depends on 26)

The computer program product of claim 26, wherein the first set of codes is further configured to cause the computer to identify the current loan state based on currency or delinquency of the one or more loan accounts.

### Claim 33 (depends on 26)

The computer program product of claim 26, wherein the first set of codes is further configured to cause the computer to identify, for each of the one or more loan accounts, a current loan state grouping from amongst a plurality of current loan state groupings.

### Claim 34 (depends on 26)

The computer program product of claim 26, wherein the first set of codes is further configured to cause the computer to identify, for each of the one or more loan accounts, the current loan state grouping from amongst the plurality of current loan state groupings, wherein the plurality of current loan state groupings include a first grouping that includes loan accounts currently less than ninety days delinquent, a second grouping that includes loan accounts currently ninety to one hundred and seventy-nine days delinquent and a third grouping that includes loan accounts currently greater than or equal to one hundred and eighty days delinquent.

### Claim 35 (depends on 26)

The computer program product of claim 26, wherein the second set of codes is further configured to cause the computer to predict the future loan state for each of the one or more loan accounts based on the identified current loan state grouping.

### Claim 36 (depends on 26)

The computer program product of claim 26, wherein the second set of codes is further configured to cause the computer to predict the future loan state for each of the one or more loan accounts based on historical loan account-specific data.

### Claim 37 (depends on 26)

The computer program product of claim 26, wherein the first set of codes is further configured to cause the computer to identity a plurality of existing loan accounts and a plurality of planned new loan accounts opening during an ensuing time period defined by the predetermined time interval.
