DUAL-OPTIMIZATION OF TARGETED DIGITAL ASSETS UNDER VOLUME AND POSITION CONSTRAINTS
Branded content, or a target asset, may be included in a set of ordered assets based on the category of an anchor asset. Fill rates, total views of the target asset, or a combination may be used in selecting an optimization strategy. A dual optimization may be used to reduce the burden of presentation based on historical yield rates and follow-on rates observed from category transition data. Serendipity may be incorporated in the process through use of a reserve pool of transitions.
1 . A computer-implemented method, comprising:
identifying, by one or more computing devices, a user to be allowed within a specific time window to use a user computing device to access a target video content;
in response to determining, by the one or more computing devices, that the user selects a first video content in a plurality of video contents, performing:
retrieving, by the one or more computing devices, traversal costs among different video content categories, wherein the plurality of video contents are partitioned into the different video content categories, wherein the first video content belongs to a first video content category of the different video content categories;
retrieving, by the one or more computing devices, a selection probability associated with the first video content category in relation to the target video content;
selecting, by the one or more computing devices, a set of sequentially ordered video contents including the target video content following the first video content, wherein the set of sequentially ordered video contents is selected from the plurality of video contents based at least in part on the traversal costs and the selection probability;
creating, by the one or more computing devices, a playlist comprising an access pointer for the user computing device to access each video content in the set of sequentially ordered video contents;
sending to the user computing device, by the one or more computing devices, the playlist for accessing and displaying at least one video content in the set of sequentially ordered video contents on the user computing device.
2 . The method of claim 1 , wherein the selection probability is computed based on historical user interaction data to indicate a probability of a user selecting the target video content for playback subsequent to playing back the first video content.
3 . The method of claim 1 , wherein the set of sequentially ordered video contents includes one or more video contents in a specific video content group that has a relatively high probability of playing back follow-on video contents in the plurality of video contents after the target video content is played back.
4 . The method of claim 3 , wherein the relatively high probability of the specific video content is identified based on historical user interaction data.
5 . The method of claim 1 , wherein the user computing device presents the target video content within the specific time window after at least one non-target video content in a video content category specifically selected from among the different video content categories.
6 . The method of claim 1 , wherein the target electronic asset is placed at a specific position in the set of sequentially ordered video contents.
7 . The method of claim 1 , wherein the selection probability is updated based on further user interaction data collected from a plurality of user computing devices.
8 . A system, comprising:
one or more computing devices;
one or more non-transitory computer readable media storing a program of instructions that is executable by the one or more computing devices to perform:
identifying, by the one or more computing devices, a user to be allowed within a specific time window to use a user computing device to access a target video content;
in response to determining, by the one or more computing devices, that the user selects a first video content in a plurality of video contents, performing:
retrieving, by the one or more computing devices, traversal costs among different video content categories, wherein the plurality of video contents are partitioned into the different video content categories, wherein the first video content belongs to a first video content category of the different video content categories;
retrieving, by the one or more computing devices, a selection probability associated with the first video content category in relation to the target video content;
selecting, by the one or more computing devices, a set of sequentially ordered video contents including the target video content following the first video content, wherein the set of sequentially ordered video contents is selected from the plurality of video contents based at least in part on the traversal costs and the selection probability;
creating, by the one or more computing devices, a playlist comprising an access pointer for the user computing device to access each video content in the set of sequentially ordered video contents,
sending to the user computing device, by the one or more computing devices, the playlist for accessing and displaying at least one video content in the set of sequentially ordered video contents on the user computing device.
9 . The system of claim 8 , wherein the selection probability is computed based on historical user interaction data to indicate a probability of a user selecting the target video content for playback subsequent to playing back the first video content.
10 . The system of claim 8 , wherein the set of sequentially ordered video contents includes one or more video contents in a specific video content group that has a relatively high probability of playing back follow-on video contents in the plurality of video contents after the target video content is played back.
11 . The system of claim 10 , wherein the relatively high probability of the specific video content is identified based on historical user interaction data.
12 . The system of claim 8 , wherein the user computing device presents the target video content within the specific time window after at least one non-target video content in a video content category specifically selected from among the different video content categories.
13 . The system of claim 8 , wherein the target electronic asset is placed at a specific position in the set of sequentially ordered video contents.
14 . The system of claim 8 , wherein the selection probability is updated based on further user interaction data collected from a plurality of user computing devices.
15 . One or more non-transitory computer-readable storage media, storing one or more sequences of instructions, which when executed by one or more processors cause performance of:
identifying, by the one or more computing devices, a user to be allowed within a specific time window to use a user computing device to access a target video content;
in response to determining, by the one or more computing devices, that the user selects a first video content in a plurality of video contents, performing:
retrieving, by the one or more computing devices, traversal costs among different video content categories, wherein the plurality of video contents are partitioned into the different video content categories, wherein the first video content belongs to a first video content category of the different video content categories;
retrieving, by the one or more computing devices, a selection probability associated with the first video content category in relation to the target video content;
selecting, by the one or more computing devices, a set of sequentially ordered video contents including the target video content following the first video content, wherein the set of sequentially ordered video contents is selected from the plurality of video contents based at least in part on the traversal costs and the selection probability;
creating, by the one or more computing devices, a playlist comprising an access pointer for the user computing device to access each video content in the set of sequentially ordered video contents;
sending to the user computing device, by the one or more computing devices, the playlist for accessing and displaying at least one video content in the set of sequentially ordered video contents on the user computing device.
16 . The one or more non-transitory computer-readable storage media of claim 15 , wherein the selection probability is computed based on historical user interaction data to indicate a probability of a user selecting the target video content for playback subsequent to playing back the first video content.
17 . The one or more non-transitory computer-readable storage media of claim 15 , wherein the set of sequentially ordered video contents includes one or more video contents in a specific video content group that has a relatively high probability of playing back follow-on video contents in the plurality of video contents after the target video content is played back.
18 . The one or more non-transitory computer-readable storage media of claim 15 , wherein the user computing device presents the target video content within the specific time window after at least one non-target video content in a video content category specifically selected from among the different video content categories.
19 . The one or more non-transitory computer-readable storage media of claim 15 , wherein the target electronic asset is placed at a specific position in the set of sequentially ordered video contents.
20 . The one or more non-transitory computer-readable storage media of claim 15 , wherein the selection probability is updated based on further user interaction data collected from a plurality of user computing devices.