Granted Patent B1

US 12,340,383 · App. 18/336,916 · Granted Jun 24, 2025

Inventors: Brian Holligan (San Francisco, CA); Andy Mahdavi (San Francisco, CA)

Assignee: DOMA TECHNOLOGY LLC

G06Q30/0202G06N20/00G06Q30/0201G06Q50/16

Abstract

Claims (76)

1. A method comprising:

obtaining, from one or more sources, a plurality of data points associated with a specified parcel of real property;

extracting specific mortgage information from the plurality of data points, comprising:

i) identifying each mortgage recorded against the parcel;

ii) identifying an indication of whether the mortgage is open; and

iii) generating a set of potentially open mortgages, including discarding any mortgages recorded against the parcel having an indication that the mortgage is closed;

providing, as input to a machine learning model, the specific mortgage information corresponding to the set of potentially open mortgages, wherein the machine learning model is trained using a training set comprising a collection of data points and labels for a set of real property parcels distinct from the specified parcel of real property, wherein each real property parcel of the training set includes information about each mortgage attached to the parcel;

generating, by the machine learning model, a prediction for each potentially open mortgage in the set of potentially open mortgages, wherein the prediction indicates a likelihood that a potentially open mortgage attached to the specified parcel of real property is actually open;

for each potentially open mortgage:

determining whether the prediction for the potentially open mortgage satisfies a threshold value; and

determining the potentially open mortgage to be closed or open based on whether or not the prediction satisfies the threshold value; and

using the determination of each potentially open mortgage as either closed or open to determine a risk tolerance for the parcel of real property and, based on the risk tolerance, determining whether to manually resolve open mortgages or allow a title evaluation process to proceed for the parcel of real property.

2. The method of claim 1 , wherein in response to determining that the prediction for a particular potentially open mortgage does not satisfy the threshold value, passing the particular potentially open mortgage for manual evaluation.

3. The method of claim 1 , wherein the threshold value is specified according to a particular defined risk tolerance.

4. The method of claim 1 , wherein the threshold value is specified based on historical information on title defects resulting from unaccounted for open mortgages and a value of corresponding title insurance claims.

5. The method of claim 1 , further comprising:

determining that each potentially open mortgage satisfies the threshold value and is determined to be closed;

determining one or more additional risk scores for the parcel of real property; and

determining based on all potentially open mortgages being closed and the one or more additional risk scores that a title policy is issuable without further human review.

6. The method of claim 1 , further comprising:

determining that, for a plurality of evaluated parcels of real property, that a higher number of errors in determining open mortgages than expected occurs; and

adjusting the threshold value for determining the potentially open mortgage to be closed.

7. The method of claim 1 , further comprising:

obtaining an additional training set that comprises an additional collection of data points and labels for an additional set of real property parcels; and

retraining the machine learning model using the additional training set.

8. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:

obtaining, from one or more sources, a plurality of data points associated with a specified parcel of real property;

extracting specific mortgage information from the plurality of data points, comprising:

i) identifying each mortgage recorded against the parcel;

ii) identifying an indication of whether the mortgage is open; and

iii) generating a set of potentially open mortgages, including discarding any mortgages recorded against the parcel having an indication that the mortgage is closed;

providing, as input to a machine learning model, the specific mortgage information corresponding to the set of potentially open mortgages, wherein the machine learning model is trained using a training set comprising a collection of data points and labels for a set of real property parcels distinct from the specified parcel of real property, wherein each real property parcel of the training set includes information about each mortgage attached to the parcel;

generating, by the machine learning model, a prediction for each potentially open mortgage in the set of potentially open mortgages, wherein the prediction indicates a likelihood that a potentially open mortgage attached to the specified parcel of real property is actually open;

for each potentially open mortgage:

determining whether the prediction for the potentially open mortgage satisfies a threshold value; and

determining the potentially open mortgage to be closed or open based on whether or not the prediction satisfies the threshold value; and

using the determination of each potentially open mortgage as either closed or open to determine a risk tolerance for the parcel of real property and, based on the risk tolerance, determining whether to manually resolve open mortgages or allow a title evaluation process to proceed for the parcel of real property.

9. The system of claim 8 , wherein in response to determining that the prediction for a particular potentially open mortgage does not satisfy the threshold value, passing the particular potentially open mortgage for manual evaluation.

10. The system of claim 8 , wherein the threshold value is specified according to a particular defined risk tolerance.

11. The system of claim 8 , wherein the threshold value is specified based on historical information on title defects resulting from unaccounted for open mortgages and a value of corresponding title insurance claims.

12. The system of claim 8 , further comprising instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:

determining that each potentially open mortgage satisfies the threshold value and is determined to be closed;

determining one or more additional risk scores for the parcel of real property; and

determining based on all potentially open mortgages being closed and the one or more additional risk scores that a title policy is issuable without further human review.

13. The system of claim 8 , further comprising instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:

determining that, for a plurality of evaluated parcels of real property, that a higher number of errors in determining open mortgages than expected occurs; and

adjusting the threshold value for determining the potentially open mortgage to be closed.

14. The system of claim 8 , further comprising instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:

obtaining an additional training set that comprises an additional collection of data points and labels for an additional set of real property parcels; and

retraining the machine learning model using the additional training set.

15. One or more non-transitory computer storage media encoded with computer program instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

obtaining, from one or more sources, a plurality of data points associated with a specified parcel of real property;

extracting specific mortgage information from the plurality of data points, comprising:

i) identifying each mortgage recorded against the parcel;

ii) identifying an indication of whether the mortgage is open; and

iii) generating a set of potentially open mortgages, including discarding any mortgages recorded against the parcel having an indication that the mortgage is closed;

providing, as input to a machine learning model, the specific mortgage information corresponding to the set of potentially open mortgages, wherein the machine learning model is trained using a training set comprising a collection of data points and labels for a set of real property parcels distinct from the specified parcel of real property, wherein each real property parcel of the training set includes information about each mortgage attached to the parcel;

generating, by the machine learning model, a prediction for each potentially open mortgage in the set of potentially open mortgages, wherein the prediction indicates a likelihood that a potentially open mortgage attached to the specified parcel of real property is actually open;

for each potentially open mortgage:

determining whether the prediction for the potentially open mortgage satisfies a threshold value; and

determining the potentially open mortgage to be closed or open based on whether or not the prediction satisfies the threshold value; and

using the determination of each potentially open mortgage as either closed or open to determine a risk tolerance for the parcel of real property and, based on the risk tolerance, determining whether to manually resolve open mortgages or allow a title evaluation process to proceed for the parcel of real property.

16. The non-transitory computer storage media of claim 15 , wherein in response to determining that the prediction for a particular potentially open mortgage does not satisfy the threshold value, passing the particular potentially open mortgage for manual evaluation.

17. The non-transitory computer storage media of claim 15 , wherein the threshold value is specified according to a particular defined risk tolerance.

18. The non-transitory computer storage media of claim 15 , wherein the threshold value is specified based on historical information on title defects resulting from unaccounted for open mortgages and a value of corresponding title insurance claims.

19. The non-transitory computer storage media of claim 15 , further comprising computer program instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

determining that each potentially open mortgage satisfies the threshold value and is determined to be closed;

determining one or more additional risk scores for the parcel of real property; and

determining based on all potentially open mortgages being closed and the one or more additional risk scores that a title policy is issuable without further human review.

20. The non-transitory computer storage media of claim 15 , further comprising computer program instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

determining that, for a plurality of evaluated parcels of real property, that a higher number of errors in determining open mortgages than expected occurs; and

adjusting the threshold value for determining the potentially open mortgage to be closed.

21. The non-transitory computer storage media of claim 15 , further comprising computer program instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

obtaining an additional training set that comprises an additional collection of data points and labels for an additional set of real property parcels; and

retraining the machine learning model using the additional training set.

Assignments (5)

Continuity (2)

References Cited (49)

Cited By (1)

US 12,602,600