Predictive detection of real-time and future viewability
Predict whether active viewability is taking place and/or the likelihood that active viewability will be taking place in the future is described. Historical viewing data may be obtained. One or more probability distribution functions may be generated based on the historical viewing data. One or more survival curves may be determined based on the one or more probability distribution functions. Current viewing data may be obtained. Whether viewability is active in at least one of a current time or a specified future time may be predicted based on the one or more probability distribution functions and the current viewing data. Alternatively, this prediction may be performed via a machine learning model trained on the historical viewing data. Whether to perform a function may be determined based on the prediction.
1. A method comprising:
obtaining historical viewing data including a first set of viewing data, where a playback device is powered on and an internal tuner or an external set top box is powered on, and a second set of viewing data, where the playback device is powered off and the internal tuner or the external set top box is powered on;
training a machine learning model based on the first set of viewing data and the second set of viewing data;
receiving current viewing data;
predicting, based on the machine learning model, and for a current time, date, and length of tune event or specified future time, date, and length of tune event, whether the playback device, connected to the internal tuner or the external set top box that is powered on, is powered on or is powered off; and
determining, based on the prediction of whether the playback device is powered on or is powered off, whether to perform a function.
2. The method of claim 1 , wherein determining whether to perform the function comprises determining to insert a targeted advertisement.
3. The method of claim 1 , wherein determining whether to perform the function comprises determining whether to deploy a firmware update or to execute other maintenance activities.
4. The method of claim 1 , wherein the historical viewing data indicates at least one of a channel change, a playback of a program, a recording of a program, or a change in playback of a program.
5. The method of claim 1 , wherein the current viewing data indicates at least one of a day, a daypart, a network, a network genre, or a type of content distribution service.
6. An apparatus comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the apparatus to:
obtain historical viewing data including a first set of viewing data, where a playback device is powered on and an internal tuner or an external set top box is powered on, and a second set of viewing data, where the playback device is powered off and the internal tuner or the external set top box is powered on;
train a machine learning model based on the first set of viewing data and the second set of viewing data;
receive current viewing data;
predict, based on the machine learning model, and for a current time, date, and length of tune event or specified future time, date, and length of tune event, whether the playback device, connected to the internal tuner or the external set top box that is powered on, is powered on or is powered off, and
determine, based on the prediction of whether the playback device is powered on or is powered off, whether to perform a function.
7. The apparatus of claim 6 , wherein the instructions, when executed, cause the apparatus to determine whether to perform the function by determining whether to insert a targeted advertisement.
8. The apparatus of claim 6 , wherein the instructions, when executed, cause the apparatus to determine whether to perform the function by determining whether to deploy a firmware update or to execute other maintenance activities.
9. The apparatus of claim 6 , wherein the historical viewing data indicates at least one of a channel change, a playback of a program, a recording of a program, or a change in playback of a program.
10. The apparatus of claim 6 , wherein the current viewing data indicates at least one of a day, a daypart, a network, a network genre, or a type of content distribution service.
11. A non-transitory computer-readable medium comprising computer-executable instructions which, when executed by at least one processor, cause the at least one processor to:
obtain historical viewing data including a first set of viewing data, where a playback device is powered on and an internal tuner or an external set top box is powered on, and a second set of viewing data, where the playback device is powered off and the internal tuner or the external set top box is powered on;
train a machine learning model based on the first set of viewing data and the second set of viewing data;
receive current viewing data;
predict, based on the machine learning model, and for a current time, date, and length of tune event or specified future time, date, and length of tune event, whether the playback device, connected to the internal tuner or the external set top box that is powered on, is powered on or is powered off; and
determine, based on the prediction of whether the playback device is powered on or is powered off, whether to perform a function.
12. The non-transitory computer-readable medium of claim 11 , wherein the instructions, when executed, cause the at least one processor to determine whether to perform the function by determining whether to insert a targeted advertisement.
13. The non-transitory computer-readable medium of claim 11 , wherein the instructions, when executed, cause the at least one processor to determine whether to perform the function by determining whether to deploy a firmware update or to execute other maintenance activities.
14. The non-transitory computer-readable medium of claim 11 , wherein the historical viewing data indicates at least one of a channel change, a playback of a program, a recording of a program, or a change in playback of a program.
15. The non-transitory computer-readable medium of claim 11 , wherein the current viewing data indicates at least one of a day, a daypart, a network, a network genre, or a type of content distribution service.