Systems and methods of personifying viewership data
A method may include receiving training data including tuning data, household member data, and initial person level distributions. The method may further include aggregating the tuning data from one or more user devices associated with a household to generate an observed household distribution, and calculating, via a prediction model, an implied household viewership distribution based on the person level distribution associated with one or more members of the household. The method may further include comparing the implied household distribution to the observed household distribution of the household, adjusting the prediction model and/or the person level distributions such that the implied household distribution more closely aligns with the observed household distribution, and generating a report with the person level distributions. A system and a non-transitory computer-readable medium may perform the method.
1. A method comprising:
receiving training data including tuning data, household member data, and initial person level viewership distribution data;
aggregating the tuning data from one or more user devices associated with a household to generate an observed household viewership distribution;
calculating, via a prediction model, an implied household viewership distribution based on the initial person level viewership distribution data associated with one or more members of the household;
comparing the implied household viewership distribution to the observed household viewership distribution;
adjusting, based on the comparison of the implied household viewership distribution to the observed household viewership distribution, the prediction model and/or the initial person level viewership distribution data such that the implied household viewership distribution more closely aligns with the observed household viewership distribution;
calculating an updated implied household viewership distribution based on the adjusted prediction model and/or the adjusted person level viewership distribution data;
comparing the updated implied household viewership distribution to the observed household viewership distribution;
adjusting, based on the comparison of the updated implied household viewership distribution to the observed household viewership distribution, the adjusted person level viewership distribution data such that the updated implied household viewership distribution more closely aligns with the observed household viewership distribution; and
generating a report with the readjusted person level viewership distribution data.
2. The method of claim 1 , wherein the initial person level viewership distribution data is based on demographics including at least one of age or gender.
3. The method of claim 1 , further comprising normalizing the tuning data over a predetermined period of time to determine a percentage of time that the household views a content based on the total number of household viewing hours over the predetermined period of time.
4. The method of claim 1 , wherein the observed household viewership distribution is independent of the temporal order of the tuning data.
5. The method of claim 1 , further comprising:
monitoring, via panelist software executing on a user device and/or a receiver, viewing events displayed by the user device and/or the receiver for a panelist household; and
generating the tuning data based on the viewing events.
6. The method of claim 1 , wherein the prediction model is based on n-way co-viewership, where n is the number of members of the household.
7. The method of claim 1 , wherein the initial person level viewership distribution data is based on one or more of household data with a single member, survey data, and/or panel data.
8. The method of claim 1 , further comprising selecting the prediction model from among a plurality of prediction models based on a number of members in the household and/or a demographic of at least one of the members.
9. The method of claim 1 , wherein the prediction model is used to calculate the implied household viewership distribution according to a machine-learning technique.
10. A system comprising:
at least one processor;
at least one memory comprising instructions, which when executed by the at least one processor, cause the at least one processor to:
receive training data including tuning data, household member data, and initial person level viewership distribution data;
aggregate the tuning data from one or more user devices associated with a household to generate an observed household viewership distribution;
calculate, via a prediction model, an implied household viewership distribution based on the initial person level viewership distribution data associated with one or more members of the household;
compare the implied household viewership distribution to the observed household viewership distribution;
adjust, based on the comparison of the implied household viewership distribution to the observed household viewership distribution, the prediction model and/or the initial person level viewership distribution data such that the implied household viewership distribution more closely aligns with the observed household viewership distribution;
calculate an updated implied household viewership distribution based on the adjusted prediction model and/or the adjusted person level viewership distribution data;
compare the updated implied household viewership distribution to the observed household viewership distribution;
adjust, based on the comparison of the updated implied household viewership distribution to the observed household viewership distribution, the adjusted person level viewership distribution data such that the updated implied household viewership distribution more closely aligns with the observed household viewership distribution; and
generate a report with the readjusted person level viewership distribution data.
11. The system of claim 10 , wherein the initial person level viewership distribution data is based on demographics including age and/or gender.
12. The system of claim 10 , wherein the instructions, when executed, further cause the at least one processor to normalize the tuning data over a predetermined period of time to determine a percentage of time that the household views a content based on the total number of household viewing hours over the predetermined period of time.
13. The system of claim 10 , further comprising a user device and/or receiver including panelist software configured to monitor viewing events displayed by the user device and/or the receiver of a panelist household,
wherein the instructions, when executed, further cause the at least one processor to generate the tuning data based on the viewing events.
14. The system of claim 10 , wherein the initial person level viewership distribution data is based on one or more of household data with a single member, survey data, and/or panel data.
15. The system of claim 10 , wherein the instructions, when executed, further cause the at least one processor to select the prediction model from among a plurality of prediction models based on a number of members in the household and/or a demographic of at least one of the members.
16. A non-transitory computer-readable medium storing instructions which, when executed by at least one processor, cause the at least one processor to:
receive training data including tuning data, household member data, and initial person level viewership distribution data;
aggregate the tuning data from one or more user devices associated with a household to generate an observed household viewership distribution;
calculate, via a prediction model, an implied household viewership distribution based on the initial person level viewership distribution data associated with one or more members of the household;
compare the implied household viewership distribution to the observed household viewership distribution;
adjust, based on the comparison of the implied household viewership distribution to the observed household viewership distribution, the prediction model and/or the initial person level viewership distribution data such that the implied household viewership distribution more closely aligns with the observed household viewership distribution;
calculate an updated implied household viewership distribution based on the adjusted prediction model and/or the adjusted person level viewership distribution data;
compare the updated implied household viewership distribution to the observed household viewership distribution;
adjust, based on the comparison of the updated implied household viewership distribution to the observed household viewership distribution, the adjusted person level viewership distribution data such that the updated implied household viewership distribution more closely aligns with the observed household viewership distribution; and
generate a report with the readjusted person level viewership distribution data.
17. The non-transitory computer-readable medium of claim 16 , wherein the initial person level viewership distribution data is based on demographics including age and/or gender.
18. The non-transitory computer-readable medium of claim 16 , wherein the instructions, when executed, further cause the at least one processor to normalize the tuning data over a predetermined period of time to determine a percentage of time that the household views a content based on the total number of household viewing hours over the predetermined period of time.
19. The non-transitory computer-readable medium of claim 16 , wherein the initial person level viewership distribution data is based on one or more of household data with a single member, survey data, and/or panel data.
20. The non-transitory computer-readable medium of claim 16 , wherein the instructions, when executed, further cause the at least one processor to select the prediction model from among a plurality of prediction models based on a number of members in the household and/or a demographic of at least one of the members.