Methods and systems for detecting suspicious or non-suspicious activities involving a mobile device use

1. A computer-implemented method of detecting a suspicious activity and/or a non-suspicious activity during an electronic transaction performed by a user device, comprising:

receiving, by a model building component, sample contextual data from one or more sensors of a plurality of user devices;

training, by the model building component using the sample contextual data, a machine learning model to identify suspicious and/or non-suspicious activities;

receiving, by a monitoring and detection component, contextual data from the one or more sensors of the plurality of user devices;

determining, by the monitoring and detection component and using the trained machine learning model, whether an expected behavior occurred; and

in response to determining that the expected behavior occurred:

determining, by the monitoring and detection component, a facial image in the contextual data upon determining a device transfer has occurred; and

in response to determining a post device transfer facial image is different from a pre device transfer facial image, enabling, by the monitoring and detection component, entry of user credentials, wherein the entry of the user credentials is disabled upon determining more than one users are staring at the screen of the user device at a credentials entry stage.

2. The method of claim 1 , wherein the sample contextual data comprises at least one or more of: i) vector displacement measurements received from an accelerometer of each of the plurality of user devices, ii) rotation measurements received from a gyroscope and a magnetometer of each of the plurality of user devices, iii) sound measurements received from one or more microphones of each of the plurality of user devices, or iv) image data received from one or more cameras of each of the plurality of user devices.

3. The method of claim 1 , wherein the contextual data further comprises at least one or more of: i) vector displacement measurements received from an accelerometer of the user device, ii) rotation measurements received from a gyroscope and a magnetometer of the user device, iii) sound measurements received from one or more microphones of the user device, or iv) image data received from one or more cameras of the user device.

4. The method of claim 1 , wherein the electronic transaction is terminated in response to determining the expected behavior not occurring within a predetermined amount of time.

5. The method of claim 1 , wherein the contextual data further comprises a pre-transfer facial image and a post-transfer facial image, further comprising:

in response to determining an occurrence of the expected behavior:

determining, by the monitoring and detection component, whether a first face detected in the pre-transfer facial image is different from a second face detected in the post-transfer facial image; and

in response to determining that the first face is different from the second face, enabling, by the monitoring and detection component, entry of user credentials; or

in response to determining that the first face matches the second face, disabling, by the monitoring and detection component, entry of user credentials.

6. The method of claim 1 , further comprising:

identifying, by the monitoring and detection component, a starting check point in the electronic transaction using the user device,

wherein the monitoring and detection component directs the one or more sensors of the plurality of user devices to begin transmitting the contextual data at the starting check point.

7. The method of claim 6 , further comprising:

identifying, by the monitoring and detection component, an ending check point in the electronic transaction using the user device,

wherein the monitoring and detection component directs the one or more sensors of the plurality of user devices to halt transmitting the contextual data at the ending check point.

8. A system for detecting a suspicious activity and/or a non-suspicious activity during an electronic transaction performed by a user device, comprising:

one or more processors;

a non-transitory computer readable medium storing instructions which, when executed by the one or more processors, cause the one or more processors to perform a method comprising:

receiving, by a model building component, sample contextual data from one or more sensors of a plurality of user devices;

training, by the model building component using the sample contextual data, a machine learning model to identify suspicious and/or non-suspicious activities;

receiving, by a monitoring and detection component, contextual data from the one or more sensors of the plurality of user devices;

determining, by the monitoring and detection component and using the trained machine learning model, whether an expected behavior occurred; and

in response to determining that the expected behavior occurred:

determining, by the monitoring and detection component, a facial image in the contextual data upon determining a device transfer has occurred; and

in response to determining a post device transfer facial image is different from a pre device transfer facial image, enabling, by the monitoring and detection component, entry of user credentials, wherein the entry of the user credentials is disabled upon determining more than one users are staring at the screen of the user device at a credentials entry stage.

9. The system of claim 8 , wherein the sample contextual data comprises at least one or more of: i) vector displacement measurements received from an accelerometer of each of the plurality of user devices, ii) rotation measurements received from a gyroscope and a magnetometer of each of the plurality of user devices, iii) sound measurements received from one or more microphones of each of the plurality of user devices, or iv) image data received from one or more cameras of each of the plurality of user devices.

10. The system of claim 8 , wherein the contextual data further comprises at least one or more of: i) vector displacement measurements received from an accelerometer of the user device, ii) rotation measurements received from a gyroscope and a magnetometer of the user device, iii) sound measurements received from one or more microphones of the user device, or iv) image data received from one or more cameras of the user device.

11. The system of claim 8 , wherein the electronic transaction is terminated in response to determining the expected behavior not occurring within a predetermined amount of time.

12. The system of claim 8 , wherein the contextual data further comprises a pre-transfer facial image and a post-transfer facial image and the method further comprises:

in response to determining an occurrence of the expected behavior:

determining, by the monitoring and detection component, whether a first face detected in the pre-transfer facial image is different from a second face detected in the post-transfer facial image; and

in response to determining that the first face is different from the second face, enabling, by the monitoring and detection component, entry of user credentials; or

in response to determining that the first face matches the second face, disabling, by the monitoring and detection component, entry of user credentials.

13. The system of claim 8 , wherein the method further comprises:

identifying, by the monitoring and detection component, a starting check point in the electronic transaction using the user device,

wherein the monitoring and detection component directs the one or more sensors of the plurality of user devices to begin transmitting the contextual data at the starting check point.

14. The system of claim 13 , wherein the method further comprises:

identifying, by the monitoring and detection component, an ending check point in the electronic transaction using the user device,

wherein the monitoring and detection component directs the one or more sensors of the plurality of user devices to halt transmitting the contextual data at the ending check point.

15. A non-transitory computer readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform a method of detecting a suspicious activity and/or a non-suspicious activity during an electronic transaction performed by a user device, the method comprising:

receiving, by a model building component, sample contextual data from one or more sensors of a plurality of user devices;

training, by the model building component using the sample contextual data, a machine learning model to identify suspicious and/or non-suspicious activities;

receiving, by a monitoring and detection component, contextual data from the one or more sensors of the plurality of user devices;

determining, by the monitoring and detection component and using the trained machine learning model, whether an expected behavior occurred; and

in response to determining that the expected behavior occurred:

determining, by the monitoring and detection component, a facial image in the contextual data upon determining a device transfer has occurred; and

in response to determining a post device transfer facial image is different from a pre device transfer facial image, enabling, by the monitoring and detection component, entry of user credentials, wherein the entry of the user credentials is disabled upon determining more than one users are staring at the screen of the user device at a credentials entry stage.

16. The non-transitory computer readable medium of claim 15 , wherein the sample contextual data comprises at least one or more of: i) vector displacement measurements received from an accelerometer of each of the plurality of user devices, ii) rotation measurements received from a gyroscope and a magnetometer of each of the plurality of user devices, iii) sound measurements received from one or more microphones of each of the plurality of user devices, or iv) image data received from one or more cameras of each of the plurality of user devices.

17. The non-transitory computer readable medium of claim 15 , wherein the contextual data further comprises at least one or more of: i) vector displacement measurements received from an accelerometer of the user device, ii) rotation measurements received from a gyroscope and a magnetometer of the user device, iii) sound measurements received from one or more microphones of the user device, or iv) image data received from one or more cameras of the user device.

18. The non-transitory computer readable medium of claim 15 , wherein the electronic transaction is terminated in response to determining the expected behavior not occurring within a predetermined amount of time.

19. The non-transitory computer readable medium of claim 15 , wherein the contextual data further comprises a pre-transfer facial image and a post-transfer facial image and the method further comprises:

in response to determining an occurrence of the expected behavior:

determining, by the monitoring and detection component, whether a first face detected in the pre-transfer facial image is different from a second face detected in the post-transfer facial image; and

in response to determining that the first face is different from the second face, enabling, by the monitoring and detection component, entry of user credentials; or

in response to determining that the first face matches the second face, disabling, by the monitoring and detection component, entry of user credentials.

20. The non-transitory computer readable medium of claim 15 , wherein the method further comprises:

identifying, by the monitoring and detection component, a starting check point in an electronic transaction using the user device, the monitoring and detection component directing the one or more sensors of the plurality of user devices to begin transmitting the contextual data at the starting check point; and

identifying, by the monitoring and detection component, an ending check point in the electronic transaction using the user device, the monitoring and detection component directing the one or more sensors of the plurality of user devices to halt transmitting the contextual data at the ending check point.