Automating responses to authentication requests using unsupervised computer learning techniques

1. A non-transitory computer-readable medium having instructions stored thereon that are capable of execution by a mobile computing device to perform operations comprising:

receiving a first request from a server system, wherein the first request corresponds to a factor in a first multi-factor authentication procedure;

sending a response to the first request to the server system based on user input approving or denying the first request and storing values of multiple parameters associated with the first request for use in automating subsequent requests for multi-factor authentication;

receiving a second request from the server system, wherein the second request corresponds to a factor in a second multi-factor authentication procedure initiated by another computing device, wherein the second request is for authentication for a different account than the first request;

automatically generating an approval response to the second request based on output of a machine learning module that receives inputs that include values of multiple parameters for the second request and the stored values of the multiple parameters associated with the first request, wherein the approval response is automatically generated without receiving user input to automate the second request; and

sending, to the server system, the automatically generated approval response.

2. The non-transitory computer-readable medium of claim 1 , wherein the multiple parameters include a frequency of login parameter that indicates how often the user of the mobile device logs into a set of one or more accounts.

3. The non-transitory computer-readable medium of claim 1 , wherein the multiple parameters include a wearable device parameter that indicates whether a wearable device is being worn by the user of the mobile device and whether the wearable device is unlocked.

4. The non-transitory computer-readable medium of claim 1 , wherein the multiple parameters include one or more parameters that indicate personally identifiable information (PII) that is stored on the mobile device that is not shared with other devices.

5. The non-transitory computer-readable medium of claim 1 , wherein the machine learning module executes an unsupervised computer learning process to generate the output.

6. The non-transitory computer-readable medium of claim 1 , wherein the multiple parameters include a wireless signature parameter based on wireless signatures of one or more nearby devices.

7. The non-transitory computer-readable medium of claim 6 , wherein the wireless signature is a Bluetooth Low Energy (BLE) signature.

8. The non-transitory computer-readable medium of claim 1 , wherein a determination whether to automate is based on whether one or more values output from the machine learning module are in a target output space;

wherein the operations further comprise requesting user input indicating whether or not to automate in response to determining that the one or more values are outside the target output space but within a threshold distance from the target output space; and

wherein the operations further comprise updating the target output space in response to the user selecting to automate.

9. The non-transitory computer-readable medium of claim 1 , wherein program code for the machine learning module is stored on a secure circuit.

10. An apparatus, comprising:

one or more processing elements; and

one or more storage elements configured to:

receive, from a server system, a first request, wherein the first request corresponds to a factor in a first multi-factor authentication procedure;

send a response to the first request to the server system based on user input approving or denying the first request and storing values of multiple parameters associated with the first request for use in automating subsequent requests for multi-factor authentication;

receive a second request from the server system, wherein the second request corresponds to a factor in a second multi-factor authentication procedure initiated by another computing device, wherein the second request is for authentication for a different account than the first request;

automatically generate an approval response to the second request based on output of a machine learning module that receives inputs that include values of multiple parameters for the second request and the stored values of the multiple parameters associated with the first request, wherein the approval response is automatically generated without receiving user input to automate the second request; and

send, to the server system, the automatically generated approval response.

11. The apparatus of claim 10 , wherein the different account for the second request is for a different service than the account for the first request.

12. The apparatus of claim 10 , wherein the multiple parameters include a wireless signature parameter that indicates wireless signatures of one or more nearby devices.

13. The apparatus of claim 10 , wherein the multiple parameters include a frequency of login parameter that indicates how often the user of a mobile device logs in to a set of one or more accounts.

14. The apparatus of claim 10 , wherein the multiple parameters include a wearable device parameter that indicates whether the wearable device is unlocked.

15. The apparatus of claim 10 , wherein the multiple parameters include one or more parameters that are based on personally identifiable information (PII) that is stored on a mobile device that is not shared with other devices.

16. A method comprising:

receiving, by a computing system from a server system, a first request, wherein the first request corresponds to a factor in a first multi-factor authentication procedure;

sending, by the computing system to the server system, a response to the first request based on user input approving or denying the first request and storing values of multiple parameters associated with the first request for use in automating subsequent requests for multi-factor authentication;

receiving, by the computing system from the server system, a second request, wherein the second request corresponds to a factor in a second multi-factor authentication procedure initiated by another computing device, wherein the second request is for authentication for a different account than the first request;

automatically generating, by the computing system, an approval response to the second request based on output of a machine learning module that receives inputs that include values of multiple parameters for the second request and the stored values of the multiple parameters associated with the first request, wherein the approval response is automatically generated without receiving user input to automate the second request; and

sending, by the computing system to the server system, the automatically generated approval response.

17. The method of claim 16 , wherein the multiple parameters include a frequency of login parameter that indicates how often the user of the mobile device logs in to a set of one or more services.

18. The method of claim 16 , wherein the multiple parameters include one or more parameters that are based on personally identifiable information (PII) that is stored on a mobile device that is not shared with other devices.

19. The method of claim 16 , wherein the multiple parameters include a wireless signature parameter based on wireless signatures of one or more nearby devices and wherein the wireless signature is a near-field communication (NFC) signature.

20. The method of claim 16 , wherein a determination whether to automate is based on whether one or more output values from the machine learning module are in a target output space;

wherein the machine learning module requests user input indicating whether or not to automate when the one or more values are outside the target output space but within a threshold distance from the target output space; and

wherein the machine learning module updates the target output space in response to the user selecting to automate.