Methods and apparatus to determine when a smart device is out-of-tab
Methods, apparatus, systems and articles of manufacture to determine whether a smart device is in-tab are disclosed. An example apparatus includes memory; instructions in the apparatus; and processor circuitry to execute the instructions to: provide smart television data from a smart television as an input to a model to generate an output, the smart television data being included in population data from a population of smart televisions; determine a tab status of the smart television based on the output; in response to the tab status of the smart television being out-of-tab, remove the smart television data from the population data; and credit media based on the population data.
1. A computing system comprising:
a processor; and
a non-transitory computer-readable storage medium, having stored thereon program instructions that, upon execution by the processor, cause performance of a set of operations comprising:
generating training data based on first data from a panelist meter connected to a first smart television and second data collected by an automatic content recognition (ACR) server in communication with the first smart television and a second smart television,
wherein the second data includes a type of disconnect being at least one of a shut-off event or a disconnect-event,
wherein the shut-off event comprises one of a turn-off event, a loss-of-power event, or another shut-off event,
wherein the disconnect-event comprises one of a loss-of-network event, technical problem event, or another disconnect-event, and
wherein the second data further includes network disconnect data having a number of disconnects from a respective wireless network for the first smart television and the second smart television;
labeling the training data as in-tab or out-of-tab based on the first data and the second data indicative of the type of disconnect and whether the first smart television and the second smart television were connected to the wireless network; and
training a model based on the training data, to determine a tab status for a third smart television different than the first smart television and the second smart television.
2. The computing system of claim 1 , wherein the second data includes at least one of a media identifier, a smart television identifier, a timestamp, tuning data, or the network disconnect data.
3. The computing system of claim 1 , wherein the operations further comprise:
determining that the first smart television corresponds to the panelist by comparing the second data from the first smart television to panel data from the panelist, the panel data being meter data indicative of media exposure of the panelist.
4. The computing system of claim 3 , wherein the operations further comprise:
identifying that the first smart television corresponds to the panelist when a threshold amount of tuning data of the second data is consistent with the panel data.
5. The computing system of claim 3 , wherein the operations further comprise:
labeling the first smart television as out-of-tab when tuning data of the second data is inconsistent with meter data of the panel data.
6. The computing system of claim 1 , wherein the operations further comprise:
implementing the model to determine the tab status for the third smart television based on the first data and the second data from the first smart television and the second smart television.
7. The computing system of claim 6 , wherein the tab status is at least one of in-tab or out-of-tab.
8. The computing system of claim 6 , wherein the second data is part of fourth data from a population of smart televisions, the third smart television included in the population.
9. At least one non-transitory computer readable storage medium comprising instructions which, when executed, cause one or more processors to cause performance of a set of operations comprising:
generating training data based on first data from a panelist meter connected to a first smart television and second data collected by an automatic content recognition (ACR) server in communication with the first smart television and a second smart television,
wherein the second data includes a type of disconnect being at least one of a shut-off event or a disconnect-event,
wherein the shut-off event comprises one of a turn-off event, a loss-of-power event, or another shut-off event,
wherein the disconnect-event comprises one of a loss-of-network event, technical problem event, or another disconnect-event, and
wherein the second data further includes network disconnect data having a number of disconnects from a respective wireless network for the first smart television and the second smart television;
labeling the training data as in-tab or out-of-tab based on the first data and the second data indicative of the type of disconnect and whether the first smart television and the second smart television were connected to the wireless network; and
training a model based on the training data, to determine a tab status for a third smart television different than the first smart television and the second smart television.
10. The at least one non-transitory computer readable storage medium of claim 9 , wherein the second data includes at least one of a media identifier, a smart television identifier, a timestamp, tuning data, or the network disconnect data.
11. The at least one non-transitory computer readable storage medium of claim 9 , the set of operations further comprising determining that the first smart television corresponds to the panelist by comparing the second data from the first smart television to panel data from the panelist, the panel data being meter data indicative of media exposure of the panelist.
12. The at least one non-transitory computer readable storage medium of claim 11 , the set of operations further comprising identifying that the first smart television corresponds to the panelist when a threshold amount of tuning data of the second data is consistent with the panel data.
13. The at least one non-transitory computer readable storage medium of claim 11 , the set of operations further comprising labeling the first smart television as out-of-tab when tuning data of the second data is inconsistent with meter data of the panel data.
14. The at least one non-transitory computer readable storage medium of claim 9 , the set of operations further comprising implementing the model to determine the tab status for the third smart television based on the first data and the second data from the first smart television and the second smart television.
15. The at least one non-transitory computer readable storage medium of claim 14 , wherein the tab status is at least one of in-tab or out-of-tab.
16. The at least one non-transitory computer readable storage medium of claim 14 , wherein the second data is part of fourth data from a population of smart televisions, the third smart television included in the population.