Automated generation of personalized content thumbnails

1. A system comprising:

a computing platform including a processing hardware and a system memory;

the system memory storing a software code, a trained machine learning (ML) model, and a content thumbnail generator;

the processing hardware configured to execute the software code to:

receive interaction data describing interactions by a user with a plurality of content thumbnails each having a corresponding plurality of content thumbnail features;

identify, using the interaction data, an affinity by the user for at least one of the one or more content thumbnail features;

determine, using at least one of the interaction data or a predetermined business rule, content for promotion to the user;

provide a prediction, using the trained ML model and based on the affinity by the user for the at least one of the one or more content thumbnail features, of a respective desirability of each of a plurality of candidate thumbnails for promoting the content to the user;

generate, using the content thumbnail generator and the prediction based on the affinity by the user for the at least one of the one or more content thumbnail features, a thumbnail having features of one or more of the plurality of candidate thumbnails; and

display the thumbnail for promoting the content to the user.

2. The system of claim 1 , wherein the processing hardware is further configured to execute the software code to provide a graphical user interface (GUI), and to display, via the GUI, the thumbnail among a plurality of other content thumbnails for other content.

3. The system of claim 2 , wherein the processing hardware is further configured to execute the software code to:

select the plurality of other content thumbnails or arrange the display of the plurality of other content thumbnails, so as to attract the user to the thumbnail.

4. The system of claim 2 , wherein the processing hardware is further configured to execute the software code to:

receive at least one of a user rating data for the content or a second interaction data describing an interaction by the user with at least one of the thumbnail or one or more of the plurality of other content thumbnails for the other content; and

train the trained ML model using the at least one of the user rating data or the second interaction data.

5. The system of claim 1 , wherein the system memory further stores a user profile database including a content consumption history of the user, and wherein identifying the affinity by the user for the at least one content thumbnail feature further uses the content consumption history of the user.

6. The system of claim 5 , wherein the processing hardware is further configured to execute the software code to:

identify, using the user profile database, another user sharing the affinity by the user for the at least one content thumbnail feature;

obtain a predetermined thumbnail previously displayed to promote the content to the another user; and

wherein generating the thumbnail is further based on the predetermined thumbnail.

7. The system of claim 5 , wherein the interaction data and the content consumption history omit any personally identifiable information (PII) of the user.

8. The system of claim 1 , wherein the processing hardware is further configured to execute the software code to:

receive another interaction data describing interactions by another user with another plurality of content thumbnails;

identify, using the another interaction data, an affinity by the another user for at least one other content thumbnail feature;

provide another prediction, using the trained ML model and based on the affinity by the another user, of a respective desirability of each of another plurality of candidate thumbnails for the content to the another user;

generate, using the content thumbnail generator and based on the another prediction, another thumbnail using features of one or more of the another plurality of candidate thumbnails; and

display the another thumbnail to promote the content to the another user.

9. The system of claim 1 , wherein the at least one content thumbnail feature for which the user has the affinity comprises one or more of a text font, text size, conveyed mood, color palette, or one or more attributes of talent depicted by a content thumbnail.

10. The system of claim 1 , wherein the at least one content thumbnail feature for which the user has the affinity comprises an audio cue configured to be triggered by an interaction by the user with a content thumbnail.

11. A method for use by a system including a computing platform having a processing hardware and a system memory storing a software code, a trained machine learning (ML) model, and a content thumbnail generator, the method comprising:

receiving, by the software code executed by the processing hardware, interaction data describing interactions by a user with a plurality of content thumbnails each having a corresponding plurality of content thumbnail features;

identifying, by the software code executed by the processing hardware using the interaction data, an affinity by the user for at least one of the one or more content thumbnail features;

determining, by the software code executed by the processing hardware using at least one of the interaction data or a predetermined business rule, content for promotion to the user;

providing a prediction, by the software code executed by the processing hardware using the trained ML model and based on the affinity by the user for the at least one of the one or more content thumbnail features, of a respective desirability of each of a plurality of candidate thumbnails for promoting the content to the user;

generating, by the software code executed by the processing hardware using the content thumbnail generator and the prediction based on the affinity by the user for the at least one of the one or more content thumbnail features, a thumbnail having features of one or more of the plurality of candidate thumbnails; and

display, by the software code executed by the processing hardware, the thumbnail to promote the content to the user.

12. The method of claim 11 , further comprising

providing, by the software code executed by the processing hardware, a graphical user interface (GUI); and

displaying, by the software code executed by the processing hardware and via the GUI, the thumbnail among a plurality of other content thumbnails for other content.

13. The method of claim 12 , method further comprising:

selecting the plurality of other content thumbnails or arranging the display of the plurality of other content thumbnails, by the software code executed by the processing hardware, so as to attract the user to the thumbnail.

14. The method of claim 12 , further comprising:

receiving, by the software code executed by the processing hardware, at least one of a user rating data for the content or a second interaction data describing an interaction by the user with at least one of the thumbnail or one or more of the plurality of other content thumbnails for the other content; and

training, by the software code executed by the processing hardware, the trained ML model using the at least one of the user rating data or the second interaction data.

15. The method of claim 11 , wherein the system memory further stores a user profile database including a content consumption history of the user, and wherein identifying the affinity by the user for the at least one content thumbnail feature further uses the content consumption history of the user.

16. The method of claim 15 , further comprising:

identifying, by the software code executed by the processing hardware using the user profile database, another user sharing the affinity by the user for the at least one content thumbnail feature;

obtaining, by the software code executed by the processing hardware, a predetermined thumbnail previously displayed to promote the content to the another user; and

wherein generating the thumbnail is further based on the predetermined thumbnail.

17. The method of claim 15 , wherein the interaction data and the content consumption history omit any personally identifiable information (PII) of the user.

18. The method of claim 11 , further comprising:

receiving, by the software code executed by the processing hardware, another interaction data describing interactions by another user with another plurality of content thumbnails;

identifying, by the software code executed by the processing hardware using the another interaction data, an affinity by the another user for at least one other content thumbnail feature;

providing another prediction, by the software code executed by the processing hardware using the trained ML model and based on the affinity by the another user, of a respective desirability of each of another plurality of candidate thumbnails for the content to the another user;

generating, by the software code executed by the processing hardware using the content thumbnail generator and based on the another prediction, another thumbnail using features of one or more of the another plurality of candidate thumbnails; and

displaying, by the software code executed by the processing hardware, the another thumbnail to promote the content to the another user.

19. The method of claim 11 , wherein the at least one content thumbnail feature for which the user has the affinity comprises one or more of a text font, text size, conveyed mood, color palette, or one or more attributes of talent depicted by a content thumbnail.

20. The method of claim 11 , wherein the at least one content thumbnail feature for which the user has the affinity comprises an audio cue configured to be triggered by an interaction by the user with a content thumbnail.