DATA ANALYTICS MODEL FOR LOAN TREATMENT

• US 20150026035A1
• Filed: 05/23/2014
• Published: 01/22/2015
• Est. Priority Date: 04/30/2010
• Status: Abandoned Application

• Current Assignee: Corelogic Solutions LLC (CoreLogic Incorporated)
• Original Assignee: Corelogic Solutions LLC (CoreLogic Incorporated)
• Inventors: SHOWALTER, Thomas
• Application Number:
  US14/286,039
• Publication Number:
  US 20150026035A1
• Time in Patent Office: Days
• US Class Current: 705/38
• 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

Data analytics are provided in loan treatment. Various sources of data may be used to optimize or predict value for a loan. Using machine-learning and/or statistical analysis, loans or treatment best suited for a particular borrower may be determined. Due to the large amounts of data available, borrower behavior may be learned from previous behavior of others and mapped to a predictive model. Machine-learning indicates the most relevant factors in loan treatment, providing a matrix for predicting loan value or treatment success. A given borrower may be classified into one of many classes of borrower based on credit information, property information, desired loan information, real estate market information, and/or other data. Tens, hundreds, or even thousands of variables may be used to predict the optimum treatment.

Claims

1. A system for data analytics in loan treatment, the system comprising:

an input configured to receive credit report information for a person associated with a loan, property information for a specific property associated with the loan, loan information for the loan, loan treatment information for the loan, and real estate market information for a region including the specific property;

a processor configured to;

apply a cluster model, the cluster model comprising an unsupervised machine-learned classifier configured to classify a borrower of the loan and the specific property into one of a plurality of borrower-property clusters, each of the borrower-property clusters being a function of both the credit report information and the property information;

apply a net present value model, the net present value model comprising a machine-trained model configured to calculate a net present value, the processor configured to apply the net present value model as a function of the borrower-property clusters, the property information, the loan information, the loan modification information, and the real estate market information; and

an output configured to output the net present value.

2. The system of claim 1 wherein the loan treatment information comprise one of modification of the loan, foreclosure of the loan, short sale, or forbearance.

3. The system of claim 1 wherein the input is further configured to receive different loan treatment information and the processor is configured to apply the net present value model as a function of at least the different loan treatment information.

4. The system of claim 1 wherein the input comprises a network interface.

5. The system of claim 1 wherein the output comprises a display configured to output the net present value.

6. The system of claim 1 wherein the credit report information comprises metrics and the processor is configured to determine distress, capacity to pay, and willingness to pay factors from the metrics, and wherein the cluster model uses the distress, capacity to pay, and willingness to pay factors as input feature vectors.

7. The system of claim 1 wherein the processor is configured to calculate a plurality of credit factors for each of a plurality of types of debt from the credit report information, and wherein the cluster model applies the credit factors as input vectors.

8. The system of claim 1 further comprising a user selector, wherein the user selector is configured to indicate selection of one or more values of variables for the loan information, and wherein the net present value is a function of the one or more values such that a user interacts with the system to receive different outputs.

9. A non-transitory computer readable storage medium comprising instructions which, when executed by a computer system that includes a data processor and is connected to at least one data repository, perform a method comprising:

accessing, by the computer system from at least one data repository through a first communication channel, credit report information for a person associated with a loan, property information for a specific property associated with the loan, loan information for the loan, loan treatment information for the loan, and real estate market information for a region including the specific property;

applying, by the data processor, a cluster model, the cluster model comprising an unsupervised machine-learned classifier configured to classify a borrower of the loan and the specific property into one of a plurality of borrower-property clusters, each of the borrower-property clusters being a function of both the credit report information and the property information;

applying, by the data processor, a net present value model as a function of the borrower-property clusters, the property information, the loan information, the loan modification information, and the real estate market information, the net present value model comprising a machine-trained model configured to calculate a net present value; and

outputting through a second communication channel the net present value.

10. The non-transitory computer readable storage medium of claim 9 wherein the loan treatment information comprise one of modification of the loan, foreclosure of the loan, short sale, or forbearance.

11. The non-transitory computer readable storage medium of claim 9 wherein the method further comprises accessing different loan treatment information and applying the net present value model as a function of at least the different loan treatment information.

12. The non-transitory computer readable storage medium of claim 9 wherein the method comprises outputting net present value on a display.

13. The non-transitory computer readable storage medium of claim 9 wherein the credit report information comprises metrics and the method further comprises determining distress, capacity to pay, and willingness to pay factors from the metrics, and wherein the cluster model uses the distress, capacity to pay, and willingness to pay factors as input feature vectors.

14. The non-transitory computer readable storage medium of claim 9 wherein the method further comprises calculating a plurality of credit factors for each of a plurality of types of debt from the credit report information, and wherein the cluster model applies the credit factors as input vectors.

15. A computer-implemented method comprising:

accessing, by a computer system from at least one data repository through a first communication channel, credit report information for a person associated with a loan, property information for a specific property associated with the loan, loan information for the loan, and real estate market information for a region including the specific property, wherein the real estate market information includes a time on market for a region associated with the specific property, and wherein the property information including a property value, equity, or open lien amount;

applying, by the data processor, a cluster model, the cluster model comprising an unsupervised machine-learned classifier configured to classify a borrower of the loan and the specific property into one of a plurality of borrower-property clusters, each of the borrower-property clusters being a function of both the credit report information and the property information;

applying, by the data processor, a net present value model as a function of the borrower-property clusters, the property information, the loan information, the loan modification information, and the real estate market information, the net present value model comprising a machine-trained model configured to calculate a net present value; and

outputting through a second communication channel the net present value.

16. The computer-implemented method of claim 15, wherein the loan treatment information comprise one of modification of the loan, foreclosure of the loan, short sale, or forbearance.

17. The computer-implemented method of claim 15, the first communication channel comprises a wide area network.

18. The computer-implemented method of claim 15 wherein the second communication channel is different than the first communication channel.

19. The computer-implemented method of claim 15 wherein the second communication channel comprises the Internet.

20. The computer-implemented method of claim 15 wherein the credit report information comprises metrics and the method further comprises determining distress, capacity to pay, and willingness to pay factors from the metrics, and wherein the cluster model uses the distress, capacity to pay, and willingness to pay factors as input feature vectors.