Methods and apparatus to predict end of streaming media using a prediction model
Apparatus to predict end of streaming media using a prediction model are disclosed herein. Examples disclosed herein comprise a predictor to determine a bandwidth rate associated with presentation of streaming media based on monitored traffic between a user device and the streaming media, a modeler to generate a prediction model based on characteristics of the bandwidth rate, and a forecaster to determine that a time when an output of the prediction model is below a minimum bandwidth threshold is a session end time for a streaming media session, the session end time corresponding to when the user device stops receiving the streaming media.
1. An apparatus comprising:
a predictor to determine a bandwidth rate associated with presentation of streaming media based on monitored traffic between a user device and a streaming media distributor;
a modeler to generate a prediction model based on characteristics of the bandwidth rate, the characteristics of the bandwidth rate including an amplitude of the bandwidth rate, a mean value of the bandwidth rate, and a standard deviation of the bandwidth rate; and
a forecaster to determine that a time when an output of the prediction model is below a minimum bandwidth threshold is a session end time for a streaming media session, the session end time corresponding to when the user device stops receiving the streaming media.
2. The apparatus of claim 1 , further including:
an identifier to determine a type of the streaming media presented on the user device; and
a threshold generator to set a bandwidth threshold based on the type of the streaming media.
3. The apparatus of claim 2 , wherein the type of the streaming media is at least one of video and audio.
4. The apparatus of claim 2 , further including a parameter generator to determine a decay factor for the prediction model based on the type of the streaming media.
5. The apparatus of claim 4 , wherein the parameter generator is further to calculate prediction model parameters by:
determining the mean value of the bandwidth rate;
determining the amplitude of the bandwidth rate; and
determining the standard deviation of the bandwidth rate.
6. The apparatus of claim 1 , wherein the bandwidth rate further includes a timestamp associated with the bandwidth rate.
7. The apparatus of claim 1 , wherein the bandwidth rate is not received from a proxy that is intermediate to a streaming media application presenting the streaming media and is not received from a streaming media distributor transmitting the streaming media to the streaming media application.
8. An apparatus, comprising:
means for determining a bandwidth rate associated with presentation of streaming media based on monitored traffic between a user device and a streaming media distributor;
means for generating a prediction model based on characteristics of the bandwidth rate, the characteristics of the bandwidth rate including an amplitude of the bandwidth rate, a mean value of the bandwidth rate, and a standard deviation of the bandwidth rate; and
means for determining that a time when an output of the prediction model is below a minimum bandwidth threshold is a session end time for a streaming media session, the session end time corresponding to when the user device stops receiving the streaming media.
9. The apparatus of claim 8 , further including:
means for determining a type of the streaming media presented on the user device; and
means for setting a bandwidth threshold based on the type of the streaming media.
10. The apparatus of claim 9 , wherein the type of the streaming media is at least one of video and audio.
11. The apparatus of claim 9 , further including means for determining a decay factor for the prediction model based on the type of the streaming media.
12. The apparatus of claim 11 , further including means for calculating prediction model parameters by:
determining the mean value of the bandwidth rate;
determining the amplitude of the bandwidth rate; and
determining the standard deviation of the bandwidth rate.
13. The apparatus of claim 8 , wherein the bandwidth rate further includes a timestamp associated with the bandwidth rate.
14. The apparatus of claim 8 , wherein the bandwidth rate is not received from a proxy that is intermediate to a streaming media application presenting the streaming media and is not received from a streaming media distributor transmitting the streaming media to the streaming media application.
15. A non-transitory computer readable medium comprising instructions that, when executed, cause a machine to, at least:
determine a bandwidth rate associated with presentation of streaming media based on monitored traffic between a user device and a streaming media distributor;
generate a prediction model based on characteristics of the bandwidth rate, the characteristics of the bandwidth rate including an amplitude of the bandwidth rate, a mean value of the bandwidth rate, and a standard deviation of the bandwidth rate; and
determine that a time when an output of the prediction model is below a minimum bandwidth threshold is a session end time for a streaming media session, the session end time corresponding to when the user device stops receiving the streaming media.
16. The non-transitory computer readable storage medium as defined in claim 15 , further including instructions that, when executed, cause the machine to:
determine a type of the streaming media presented on the user device; and
set a bandwidth threshold based on the type of the streaming media.
17. The non-transitory computer readable storage medium of claim 16 , wherein the type of the streaming media is at least one of video and audio.
18. The non-transitory computer readable storage medium as defined in claim 16 , further including instructions that, when executed, cause the machine to determine a decay factor for the prediction model based on the type of the streaming media.
19. The non-transitory computer readable storage medium as defined in claim 18 , further including instructions that, when executed, cause the machine to calculate prediction model parameters by:
determining the mean value of the bandwidth rate;
determining the amplitude of the bandwidth rate; and
determining the standard deviation of the bandwidth rate.
20. The non-transitory computer readable storage medium as defined in claim 15 , wherein the bandwidth rate further includes a timestamp associated with the bandwidth rate.
21. The non-transitory computer readable storage medium as defined in claim 15 , wherein the bandwidth rate is not received from a proxy that is intermediate to a streaming media application presenting the streaming media and is not received from a streaming media distributor transmitting the streaming media to the streaming media application.