Rendering a dynamic endemic banner on streaming platforms using content recommendation systems and content modeling for user exploration and awareness
Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for utilizing a content recommendation system powering a streaming media publisher channel to enhance an ad creative being shown to the user via awareness or performance campaigns. This method allows the platform to present exploratory personalized in-channel content to the publisher platform users in endemic banners that run on the platform which then correspondingly helps drive user reach. An example embodiment operates by implementing personalized content banners that may act as a hook for channel users opening their streaming device, both active and lapsed, to enter back into the channel.
1. A computer-implemented method for creating dynamic banners, the method comprising:
generating, by at least one computer processor and based on a trained machine learning model, a first call to a content recommendation system for a first subset of content assets for a target banner template, wherein the first subset of content assets includes content reflecting interests of a user;
generating, based on the trained machine learning model, a second call to the content recommendation system for a second subset of content assets for the target banner template, wherein the second subset of content assets includes content related to the interests of the user and differs from the first subset of content assets, wherein the trained machine learning model is trained to weight content asset subset generation based on the target banner template, including at least the second subset of content assets being selected by the user at a frequency above a threshold value;
generating, based on the trained machine learning model, a third call to the content recommendation system for a third subset of content assets for the target banner template, wherein the third subset of content assets includes content selections unrelated to the interests of the user and absent from either the first subset or the second subset of content assets;
upon receiving the first subset of content assets, the second subset of content assets, and the third subset of content assets, selecting, based on an affinity of the user for selection of the content assets, a collective set of the content assets drawn from each of the first subset of content assets, the second subset of content assets, and the third subset of content assets;
randomly selecting at least a content asset from the collective set of the content assets;
receiving, at a media device, the content asset;
stitching the content asset into the target banner template to form a composite banner; and
rendering the composite banner on a display of the media device.
2. The method of claim 1 , wherein the composite banner comprises an endemic banner.
3. The method of claim 1 , wherein the media device comprises an Over-the-Top (OTT) device.
4. The method of claim 1 , wherein the first subset of content assets comprises the content most closely matching historical interactions of the user.
5. The method of claim 1 , wherein the first subset of content assets further comprises popular current content.
6. The method of claim 1 , wherein the first subset of content assets further comprises highest rated current content.
7. The method of claim 1 , wherein the trained machine learning model comprises an exploratory component to select content assets not in the first subset or the second subset of content assets.
8. The method of claim 1 , wherein the target banner template is selected based on any of:
opening an application (App);
executing a first-time view;
subscribing to a service;
resumption of watching targeted content;
completion of watching targeted content; or
completion of watching a sponsorship program.
9. A system, comprising:
a memory; and
at least one processor coupled to the memory and configured to perform operations comprising:
generating, by at least one computer processor and based on a trained machine learning model, a first call to a content recommendation system for a first subset of content assets for a target banner template, wherein the first subset of content assets includes content reflecting interests of a user;
generating, based on the trained machine learning model, a second call to the content recommendation system for a second subset of content assets for the target banner template, wherein the second subset of content assets includes content related to the interests of the user and differs from the first subset of content assets, wherein the trained machine learning model is trained to weight content asset subset generation based on the target banner template, including at least the second subset of content assets being selected by the user at a frequency above a threshold value;
generating, based on the trained machine learning model, a third call to the content recommendation system for a third subset of content assets for the target banner template, wherein the third subset of content assets includes content selections unrelated to a the interests and absent from either the first subset or the second subset of content assets;
upon receiving the first subset of content assets, the second subset of content assets, and the third subset of content assets, selecting, based on an affinity of the user for selection of the content assets, a collective set of the content assets drawn from each of the first subset of content assets, the second subset of content assets, and the third subset of content assets;
randomly selecting at least a content asset from the collective set of the content assets;
receiving, at a media device, the content asset;
stitching the content asset into the target banner template to form a composite banner; and
rendering the composite banner on a display of the media device.
10. The system of claim 9 , where the composite banner comprises an endemic banner.
11. The system of claim 9 , where the system comprises a streaming media device platform for an Over-the-Top (OTT) device.
12. The system of claim 9 , wherein the first subset of content assets comprises the content most closely matching historical interactions of the user.
13. The system of claim 9 , wherein the first subset of content assets further comprises popular current content.
14. The system of claim 9 , wherein the first subset of content assets further comprises highest rated current content.
15. The system of claim 9 , wherein the trained machine learning model comprises an exploratory component to select content assets not in the first subset or the second subset of content assets.
16. A non-transitory computer-readable medium having instructions stored thereon that, when executed by at least one computing device, cause the at least one computing device to perform operations comprising:
generating, by at least one computer processor and based on a trained machine learning model, a first call to a content recommendation system for a first subset of content assets for a target banner template, wherein the first subset of content assets includes content reflecting interests of a user;
generating, based on the trained machine learning model, a second call to the content recommendation system for a second subset of content assets for the target banner template, wherein the second subset of content assets includes content related to the interests of the user and differs from the first subset of content assets, wherein the trained machine learning model is trained to weight content asset subset generation based on the target banner template including at least the second subset of content assets, being selected by the user at a frequency above a threshold value;
generating, based on the trained machine learning model, a third call to the content recommendation system for a third subset of content assets for the target banner template, wherein the third subset of content assets includes content selections unrelated to the interests of the user and absent from either the first subset or the second subset of content assets;
upon receiving the first subset of content assets, the second subset of content assets, and the third subset of content assets, selecting, based on an affinity of the user for selection of the content assets, a collective set of the content assets drawn from each of the first subset of content assets, the second subset of content assets, and the third subset of content assets;
randomly selecting at least a content asset from the collective set of the content assets;
receiving, at a media device, the content asset;
stitching the content asset into the target banner template to form a composite banner; and
rendering the composite banner on a display of the media device.
17. The non-transitory computer-readable medium of claim 16 , wherein the composite banner comprises an endemic banner and the at least one computing device comprises an Over-the-Top (OTT) device.
18. The non-transitory computer-readable medium of claim 16 , wherein the trained machine learning model comprises an exploratory component to select content assets not in the first subset or second subset of content assets.