Online asset recommendation system
Creating a playlist of multimedia assets based on estimated user viewing length and an estimated length of engagement during a user session. Assets are selected based on an anchor asset displayed with the playlist of multimedia assets.
1. A method, comprising:
creating a candidate list of multimedia assets from a plurality of multimedia assets for presentation to a user based on an anchor multimedia asset that is currently being consumed by the user;
as the anchor multimedia asset is being consumed by the user:
estimating an expected user viewing length of each multimedia asset in the candidate list of multimedia assets;
estimating a total length of engagement based on historical interaction data, the total length of engagement represents an estimated total amount of time available to present a set of multimedia assets that follow the anchor multimedia asset to the user;
selecting, in realtime, the set of multimedia assets from the candidate list of multimedia assets based on the expected user viewing length of a multimedia asset and a remaining estimated total length of engagement as other multimedia assets are selected for the set of multimedia assets;
creating an ordered playlist of the set of multimedia assets;
sending the ordered playlist to a receiving device.
2. The method of claim 1 , wherein the selecting the set of multimedia assets is further based on a monetary estimate of the multimedia asset based on the expected user viewing length.
3. The method of claim 1 , further comprising:
creating a cumulative aggregation of engagement data for a particular multimedia asset from users that have indicated a preferred engagement with the particular multimedia asset.
4. The method of claim 1 , further comprising:
creating a cumulative aggregation of engagement data for a particular multimedia asset from users that have indicated a preferred engagement with the particular multimedia asset;
wherein the users that have indicated a preferred engagement with the particular multimedia asset are determined to have similar characteristics.
5. The method of claim 1 , further comprising:
determining a monetary value associated with a length of engagement by a user for each multimedia asset in the list of multimedia assets within a window of engagement.
6. The method of claim 1 , wherein the estimating the total length of engagement further comprises:
assigning the user to a group to use group historical interaction data to estimate the total length of engagement.
7. The method of claim 1 , wherein the estimating the total length of engagement further comprises:
using historical interaction data of the user to estimate the total length of engagement.
8. The method of claim 1 , wherein the anchor multimedia asset is selected by the user.
9. 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:
creating a candidate list of multimedia assets from a plurality of multimedia assets for presentation to a user based on an anchor multimedia asset that is currently being consumed by the user;
as the anchor multimedia asset is being consumed by the user:
estimating an expected user viewing length of each multimedia asset in the candidate list of multimedia assets;
estimating a total length of engagement based on historical interaction data, the total length of engagement represents an estimated total amount of time available to present a set of multimedia assets that follow the anchor multimedia asset to the user;
selecting, in realtime, the set of multimedia assets from the candidate list of multimedia assets based on the expected user viewing length of a multimedia asset and a remaining estimated total length of engagement as other multimedia assets are selected for the set of multimedia assets;
creating an ordered playlist of the set of multimedia assets;
sending the ordered playlist to a receiving device.
10. The one or more non-transitory computer-readable storage media of claim 9 , wherein the selecting the set of multimedia assets is further based on a monetary estimate of the multimedia asset based on the expected user viewing length.
11. The one or more non-transitory computer-readable storage media of claim 9 , further comprising:
creating a cumulative aggregation of engagement data for a particular multimedia asset from users that have indicated a preferred engagement with the particular multimedia asset.
12. The one or more non-transitory computer-readable storage media of claim 9 , further comprising:
creating a cumulative aggregation of engagement data for a particular multimedia asset from users that have indicated a preferred engagement with the particular multimedia asset;
wherein the users that have indicated a preferred engagement with the particular multimedia asset are determined to have similar characteristics.
13. The one or more non-transitory computer-readable storage media of claim 9 , further comprising:
determining a monetary value associated with a length of engagement by a user for each multimedia asset in the list of multimedia assets within a window of engagement.
14. The one or more non-transitory computer-readable storage media of claim 9 , wherein the estimating the total length of engagement further comprises:
assigning the user to a group to use group historical interaction data to estimate the total length of engagement.
15. The one or more non-transitory computer-readable storage media of claim 9 , wherein the estimating the total length of engagement further comprises:
using historical interaction data of the user to estimate the total length of engagement.
16. The one or more non-transitory computer-readable storage media of claim 9 , wherein the anchor multimedia asset is selected by the user.
17. An apparatus, comprising:
one or more processors; and
a memory storing instructions, which when executed by the one or more processors, causes the one or more processors to:
create a candidate list of multimedia assets from a plurality of multimedia assets for presentation to a user based on an anchor multimedia asset that is currently being consumed by the user;
as the anchor multimedia asset is being consumed by the user:
estimate an expected user viewing length of each multimedia asset in the candidate list of multimedia assets;
estimate a total length of engagement based on historical interaction data, the total length of engagement represents an estimated total amount of time available to present a set of multimedia assets that follow the anchor multimedia asset to the user;
select, in realtime, the set of multimedia assets from the candidate list of multimedia assets based on the expected user viewing length of a multimedia asset and a remaining estimated total length of engagement as other multimedia assets are selected for the set of multimedia assets;
create an ordered playlist of the set of multimedia assets;
send the ordered playlist to a receiving device.
18. The apparatus of claim 17 , wherein the select the set of multimedia assets is further based on a monetary estimate of the multimedia asset based on the expected user viewing length.
19. The apparatus of claim 17 , wherein the instructions, which when executed by the one or more processors, further causes the one or more processors to:
create a cumulative aggregation of engagement data for a particular multimedia asset from users that have indicated a preferred engagement with the particular multimedia asset;
wherein the users that have indicated a preferred engagement with the particular multimedia asset are determined to have similar characteristics.
20. The apparatus of claim 17 , wherein the instructions, which when executed by the one or more processors, further causes the one or more processors to:
determine a monetary value associated with a length of engagement by a user for each multimedia asset in the list of multimedia assets within a window of engagement.