Determining content output session outliers

1. A method comprising:

receiving data indicative of a plurality of content output sessions associated with a first time period, wherein the data indicates a content identifier, a device identifier, and a duration for each content output session;

determining, based on the received data, a first subset of the plurality of content output sessions that are outlier sessions;

determining, based on the first subset of the plurality of content output sessions that are outlier sessions, a quantity of times during the first time period that each device identifier is associated with an outlier session;

classifying, based on the quantity of times during the first time period that each device identifier is associated with an outlier session, each device as an outlier device or an inlier device;

determining, based on the classification, a second subset of the first subset of content output sessions that are associated with an outlier device;

comparing, for each content output session of the second subset, the duration of the content output session to a duration threshold associated with a second time period; and

adjusting, based on the comparison, a total duration of the content output sessions of the second subset.

2. The method of claim 1 , wherein receiving the data indicative of the plurality of content output sessions associated with the first time period comprises:

retrieving, from a database, data indicative of sessions during which content was output during the first time period.

3. The method of claim 1 , wherein determining the first subset of the plurality of content output sessions that are outlier sessions is based on a distribution of the received data.

4. The method of claim 1 , wherein determining, based on the received data, the first subset of the plurality of content output sessions that are outlier sessions comprises:

determining that the first subset of the plurality of content output sessions that are outlier sessions satisfy a duration threshold associated with the first time period.

5. The method of claim 4 , wherein determining that the first subset of the plurality of content output sessions satisfy the duration threshold associated with the first time period comprises:

determining that each content output session of the first subset has a duration that exceeds the duration threshold associated with the first time period.

6. The method of claim 1 , wherein determining the quantity of times during the first time period that each device identifier is associated with the outlier session comprises:

determining a quantity of days during the first time period that each device identifier is associated with at least one outlier session and a quantity of active days during the first time period for each device identifier.

7. The method of claim 6 , wherein classifying-each device as an outlier device or an inlier device comprises:

determining, for each device, a ratio of the quantity of days during the first time period that each device identifier is associated with at least one outlier session to the quantity of active days during the first time period for each device identifier.

8. The method of claim 7 , wherein classifying each device as an outlier device or an inlier device comprises classifying-a device as an outlier device if the ratio associated with that device exceeds an outlier threshold.

9. The method of claim 7 , wherein classifying each device as an outlier device or an inlier device comprises classifying a device as an inlier device if the ratio associated with that device does not exceeds an outlier threshold.

10. The method of claim 1 , wherein the second time period has a duration that is longer than a duration of the first time period.

11. The method of claim 10 , wherein the duration threshold associated with the second time period is indicative of a median duration during which content that is output during the second time period.

12. The method of claim 1 , wherein adjusting the total duration of the content output sessions of the second subset comprises:

determining, based on the comparison, a third subset of the second subset of content output sessions associated with a duration exceeding the duration threshold.

13. The method of claim 12 , wherein adjusting the total duration of the content output sessions of the second subset further comprises:

determining a total quantity of time by which the durations associated with each of the third subset of content output sessions exceed the duration threshold.

14. The method of claim 13 , wherein adjusting the total duration of the content output sessions of the second subset further comprises:

reducing the total duration associated with the content output sessions of the second subset by the total quantity of time.

15. The method of claim 1 , wherein the content identifier comprises at least one of a channel identifier, an application identifier, or a content title.

16. The method of claim 1 , wherein the duration of each content output session of the plurality of content output sessions comprises at least one of a total time of content output for each session or a start time and an end time for each session.

17. The method of claim 1 , wherein the received data is associated with a first application of a plurality of applications.

18. The method of claim 17 , wherein the device identifier is received from another application of the plurality of applications.

19. A method comprising:

receiving data indicative of a plurality of content output sessions associated with a first time period, wherein the data indicates a content identifier, a device identifier, and a duration for each content output session;

determining, based on the received data, a first subset of the plurality of content output sessions that are outlier sessions;

classifying each device associated with a device identifier in the first subset of the plurality of content output sessions, as an outlier device or an inlier device using at least one of a gradient descent algorithm or a time decay algorithm;

determining, based on the classification, a second subset of the first subset of content output sessions that are associated with an outlier device;

comparing, for each content output session of the second subset, the duration of the content output session to a duration threshold associated with a second time period; and

adjusting, based on the comparison, a total duration of the content output sessions of the second subset.