Systems and methods for improving KBA identity authentication questions

1. A computer-implemented method comprising:

receiving a set of identity information associated with a subject;

querying one or more databases with at least a portion of the set of identity information;

receiving, in response to the querying, personally identifiable information;

determining, from the personally identifiable information, a gender of the subject;

ranking, by a predictive model executing on one or more computer processors, a plurality of question topics and associated pass rate metrics based on the gender of the subject while suppressing false-positive question topics;

selecting, based on the ranking and the gender of the subject, at least one knowledge-based authentication (KBA) proofing question for presentation to the subject, the at least one KBA proofing question having a personally identifiable correct answer;

sending, for display on a first computing device associated with the subject, the at least one KBA identity proofing question;

receiving, responsive to the sending, a response answer; and

responsive to a match between the response answer and the personally identifiable correct answer, sending, for display on the first computing device associated with the subject, a first indication of authentication.

2. The method of claim 1 , further comprising:

determining, from the personally identifiable information, an age of the subject;

further ranking the plurality of question topics and associated pass rate metrics based on the age of the subject; and

selecting the at least one KBA proofing question based on the further ranking and the age of the subject.

3. The method of claim 1 , further comprising refining the predictive model based on the match or a mismatch between the response answer and the personally identifiable correct answer.

4. The method of claim 1 , further comprising refining the predictive model based on a history of matches between the response answer and the personally identifiable correct answer to produce KBA identity proofing questions that increase a probability of a match.

5. The method of claim 4 , wherein refining the predictive model comprises applying decision tree learning.

6. The method of claim 5 , wherein applying the decision tree learning comprises applying an ID4.5 algorithm.

7. The method of claim 1 , further comprising determining one or more subject characteristics associated with the subject, wherein the one or more subject characteristics comprise a characteristic related to one or more of: age, culture, residence, vehicle, subject history, and the first computing device.

8. The method of claim 7 , wherein the characteristic related to the first computing device comprises one or more of: a phone number, an Internet Protocol (IP) address, a Media Access Control (MAC) address, a location, an indication of signal-to-noise, browser configuration information, operating system information, a listing of installed fonts, and a listing of installed plug-ins.

9. The method of claim 1 , further comprising sending, for display on the first computing device associated with the subject, an indication of authentication failure responsive to a determined mismatch between the response answer and the personally identifiable correct answer.

10. The method of claim 1 , wherein receiving the set of identity information comprises receiving one or more of: a name, an address, a gender, a birth date, a phone number, at least portion of a social security number, an IP address, a location, and a communication device electronic fingerprint.

11. A computer-implemented method comprising:

receiving a set of identity information associated with a subject;

querying one or more databases with at least a portion of the set of identity information;

receiving, in response to the querying, personally identifiable information;

determining, from the personally identifiable information, an age of the subject;

ranking, by a predictive model executing on one or more computer processors, a plurality of question topics and associated pass rate metrics based on the age of the subject while suppressing false-positive question topics;

selecting, based on the ranking and the age of the subject, at least one knowledge-based authentication (KBA) proofing question for presentation to the subject, the at least one KBA proofing question having a personally identifiable correct answer;

sending, for display on a first computing device associated with the subject, the at least one KBA identity proofing question;

receiving, responsive to the sending, a response answer; and

responsive to a match between the response answer and the personally identifiable correct answer, sending, for display on the first computing device associated with the subject, a first indication of authentication.

12. The method of claim 11 , further comprising:

determining, from the personally identifiable information, a gender of the subject;

further ranking the plurality of question topics and associated pass rate metrics based on the gender of the subject; and

selecting the at least one KBA proofing question based on the further ranking and the gender of the subject.

13. The method of claim 11 , further comprising refining the predictive model based on the match or a mismatch between the response answer and the personally identifiable correct answer.

14. The method of claim 11 , further comprising refining the predictive model based on a history of matches between the response answer and the personally identifiable correct answer to produce KBA identity proofing questions that increase a probability of a match.

15. The method of claim 11 , further comprising determining one or more subject characteristics associated with the subject, wherein the one or more subject characteristics comprise a characteristic related to one or more of: gender, culture, residence, vehicle, subject history, and the first computing device.

16. The method of claim 15 , wherein the characteristic related to the first computing device comprises one or more of: a phone number, an Internet Protocol (IP) address, a Media Access Control (MAC) address, a location, an indication of signal-to-noise, browser configuration information, operating system information, a listing of installed fonts, and a listing of installed plug-ins.

17. The method of claim 11 , further comprising sending, for display on the first computing device associated with the subject, an indication of authentication failure responsive to a determined mismatch between the response answer and the personally identifiable correct answer.

18. A non-transient computer-readable medium storing instructions, that when executed by a user device having one or more processors, cause the one or more processors to perform a method comprising:

receiving a set of identity information associated with a subject;

querying one or more databases with at least a portion of the set of identity information;

receiving, in response to the querying, personally identifiable information;

determining, from the personally identifiable information, at least one subject characteristic;

ranking, by a predictive model executing on one or more computer processors, a plurality of question topics and associated pass rate metrics based on the at least one subject characteristic while suppressing false-positive question topics;

selecting, based on the ranking and the at least one subject characteristic, at least one knowledge-based authentication (KBA) proofing question for presentation to the subject, the at least one KBA proofing question having a personally identifiable correct answer;

sending, for display on a first computing device associated with the subject, the at least one KBA identity proofing question;

receiving, responsive to the sending, a response answer; and

responsive to a match between the response answer and the personally identifiable correct answer, sending, for display on the first computing device associated with the subject, a first indication of authentication.

19. The non-transient computer-readable medium of claim 18 , further comprising:

determining, from the personally identifiable information, a gender of the subject; and

further ranking the plurality of question topics and associated pass rate metrics based on the gender of the subject.

20. The non-transient computer-readable medium of claim 18 , further comprising:

determining, from the personally identifiable information, an age of the subject; and

further ranking the plurality of question topics and associated pass rate metrics based on the age of the subject.