Managing data transmissions based on a user's digital footprint

1. A system comprising:

a processing device; and

a memory device that includes instructions executable by the processing device for causing the processing device to:

determine a first transmission pattern in which first content was transmitted to a first user device of a user, wherein the first transmission pattern resulted in the user performing an Internet activity associated with the first content using a second user device;

determine one or more characteristics of the first content;

generate training data that includes a relationship between (i) the first transmission pattern and (ii) the one or more characteristics of the first content; and

train a machine-learning-model using the training data to enable the machine-learning-model to predict a second transmission pattern in which to transmit second content that is different from the first content.

2. The system of claim 1 , wherein the first user device is an Internet-connected television, and wherein the second user device is a mobile phone, tablet, laptop computer, desktop computer, e-reader, or a wearable computer.

3. The system of claim 1 , wherein the memory device further comprises instructions executable by the processing device for causing the processing device to:

generate a digital footprint for the user, wherein the digital footprint represents Internet activities performed by the user via one or more user devices; and

determine the first transmission pattern based at least in part on the digital footprint.

4. The system of claim 1 , wherein the first transmission pattern includes multiple transmissions of the first content to the first user device over the course of multiple days.

5. The system of claim 1 , wherein the memory device further comprises instructions executable by the processing device for causing the processing device to:

determine a plurality of patterns in which a plurality of content was transmitted to the first user device during a time period, wherein the plurality of patterns resulted in the second user device performing a plurality of Internet activities corresponding to the plurality of content; and

train the machine-learning-model at least in part by using the plurality of patterns as the training data.

6. The system of claim 1 , wherein the Internet activity includes visiting a website.

7. The system of claim 1 , wherein the first content and the second content are advertisements.

8. A method comprising:

determining, by a processing device, a first transmission pattern in which first content was transmitted to a first user device of a user, wherein the first transmission pattern resulted in the user performing an Internet activity associated with the first content using a second user device;

determining, by the processing device, one or more characteristics of the first content;

generating, by the processing device, training data that includes a relationship between (i) the first transmission pattern and (ii) the one or more characteristics of the first content; and

training, by the processing device, a machine-learning-model using the training data to enable the machine-learning-model to predict a second transmission pattern in which to transmit second content that is different from the first content.

9. The method of claim 8 , wherein the first user device is an Internet-connected television, and wherein the second user device is a mobile phone, tablet, laptop computer, desktop computer, e-reader, or a wearable computer.

10. The method of claim 8 , further comprising:

generating a digital footprint for the user, wherein the digital footprint represents Internet activities performed by the user via one or more user devices; and

determining the first transmission pattern based at least in part on the digital footprint.

11. The method of claim 8 , wherein the first transmission pattern includes multiple transmissions of the first content to the first user device over the course of multiple days.

12. The method of claim 8 , further comprising:

determining a plurality of patterns in which a plurality of content was transmitted to the first user device during a time period, wherein the plurality of patterns resulted in the second user device performing a plurality of Internet activities corresponding to the plurality of content; and

training the machine-learning-model at least in part by using the plurality of patterns as the training data.

13. The method of claim 8 , wherein the Internet activity includes visiting a website.

14. The method of claim 8 , wherein the first content and the second content are advertisements.

15. A non-transitory computer-readable medium comprising program code that is executable by a processing device for causing the processing device to:

access training data that includes a relationship between (i) a first transmission pattern in which first content was transmitted to a first user device of a user and that resulted in the user performing an Internet activity associated with the first content using a second user device, and (ii) one or more characteristics of the first content; and

train a machine-learning-model using the training data to enable the machine-learning-model to predict a second transmission pattern in which to transmit second content that is different from the first content.

16. The non-transitory computer-readable medium of claim 15 , further comprising program code that is executable by the processing device for causing the processing device to:

determine the first transmission pattern;

determine one or more characteristics of the first content; and

generate the training data based on the first transmission pattern and the one or more characteristics of the first content.

17. The non-transitory computer-readable medium of claim 15 , wherein the first user device is an Internet-connected television, and wherein the second user device is a mobile phone, tablet, laptop computer, desktop computer, e-reader, or a wearable computer.

18. The non-transitory computer-readable medium of claim 15 , further comprising program code that is executable by the processing device for causing the processing device to:

generate a digital footprint for the user, wherein the digital footprint represents Internet activities performed by the user via one or more user devices; and

determine the first transmission pattern based at least in part on the digital footprint.

19. The non-transitory computer-readable medium of claim 15 , wherein the first transmission pattern includes multiple transmissions of the first content to the first user device over the course of multiple days.

20. The non-transitory computer-readable medium of claim 15 , wherein the training data includes a plurality of patterns in which a plurality of content was transmitted to the first user device during a time period, wherein the plurality of patterns resulted in the user performing a plurality of Internet activities corresponding to the plurality of content with the second user device, and wherein the machine-learning-model is trained at least in part by using the plurality of patterns as the training data.

21. The non-transitory computer-readable medium of claim 15 , wherein the Internet activity includes visiting a website, and wherein the first content and the second content are advertisements.