METHODS AND APPARATUS TO DETERMINE DEMOGRAPHIC CLASSIFICATIONS FOR CENSUS LEVEL IMPRESSION COUNTS AND UNIQUE AUDIENCE SIZES
Methods, apparatus, systems and articles of manufacture to determine demographic classifications for census level impression counts and unique audience sizes are disclosed. An example apparatus includes processor circuitry to execute instructions to execute a machine learning model to generate a probability of an occurrence of a demographic classification; generate a coviewing factor based on panel data; generate a viewer assignment output based on the coviewing factor; determine a unique audience total based on the probability of the occurrence of the demographic classification; adjust the unique audience total based on a non-coverage factor; and generate a report including the adjusted unique audience total.
1 . An apparatus comprising:
memory;
instructions; and
processor circuitry to execute the instructions to:
execute a machine learning model to generate a probability of an occurrence of a demographic classification;
generate a coviewing factor based on panel data;
generate a viewer assignment output based on the coviewing factor;
determine a unique audience total based on the probability of the occurrence of the demographic classification;
adjust the unique audience total based on a non-coverage factor; and
generate a report including the adjusted unique audience total.
2 . The apparatus of claim 1 , wherein the machine learning model is trained using media tag impressions matched with panel members.
3 . The apparatus of claim 1 , wherein the machine learning model is trained using media exposure data reformatted to match a format of a media tag impression.
4 . The apparatus of claim 1 , wherein the processor circuitry is to generate the non-coverage factor by dividing a count of covered impressions to a count of measurable impressions, the covered impressions including impressions linked to a database proprietor home, the measurable impressions including the covered impressions and non-covered impressions, the non-covered impressions including impressions not linked to a database proprietor home, the count of the covered impressions and the count of the measurable impressions included in the viewer assignment output.
5 . The apparatus of claim 4 , wherein the processor circuitry is to adjust the unique audience total by:
aggregating a covered impressions total and a covered unique audience total from the viewer assignment output;
combining the non-coverage factor with the aggregated covered impressions and unique audience total;
deriving non-coverage frequency by dividing the covered impressions total by the covered unique audience total; and
adjusting the unique audience total by dividing the total impressions total by the non-coverage frequency.
6 . The apparatus of claim 1 , wherein the processor circuitry is to:
match identification data in a media tag with personal information; and
input the matched media tag into the machine learning model to generate the probability of the occurrence of the demographic classification.
7 . The apparatus of claim 1 , wherein the processor circuitry is to:
determine the unique audience total for a demographic based on the probability of the occurrence of the demographic classification;
adjust the unique audience total of the demographic based on the non-coverage factor, the non-coverage factor corresponding to the demographic; and
include the adjusted unique audience total for the demographic in the report.
8 . A non-transitory computer readable medium comprising instructions which, when executed, cause one or more processors to at least:
execute a machine learning model to generate a probability of an occurrence of a demographic classification;
generate a coviewing factor based on panel data;
generate a viewer assignment output based on the coviewing factor;
determine a unique audience total based on the probability of the occurrence of the demographic classification;
adjust the unique audience total based on a non-coverage factor; and
generate a report including the adjusted unique audience total.
9 . The computer readable medium of claim 8 , wherein the machine learning model is trained using media tag impressions matched with panel members.
10 . The computer readable medium of claim 8 , wherein the machine learning model is trained using media exposure data reformatted to match a format of a media tag impression.
11 . The computer readable medium of claim 8 , wherein the instructions cause the one or more processors to generate the non-coverage factor by dividing a count of covered impressions to a count of measurable impressions, the covered impressions including impressions linked to a database proprietor home, the measurable impressions including the covered impressions and non-covered impressions, the non-covered impressions including impressions not linked to a database proprietor home, the count of the covered impressions and the count of the measurable impressions included in the viewer assignment output.
12 . The computer readable medium of claim 11 , wherein the instructions cause the one or more processors to adjust the unique audience total by:
aggregating a covered impressions total and a covered unique audience total from the viewer assignment output;
combining the non-coverage factor with the aggregated covered impressions and unique audience total;
deriving non-coverage frequency by dividing the covered impressions total by the covered unique audience total; and
adjusting the unique audience total by dividing the total impressions total by the non-coverage frequency.
13 . The computer readable medium of claim 8 , wherein the instructions cause the one or more processors to:
match identification data in a media tag with personal information; and
input the matched media tag into the machine learning model to generate the probability of the occurrence of the demographic classification.
14 . The computer readable medium of claim 8 , wherein the instructions cause the one or more processors to:
determine the unique audience total for a demographic based on the probability of the occurrence of the demographic classification;
adjust the unique audience total of the demographic based on the non-coverage factor, the non-coverage factor corresponding to the demographic; and
include the adjusted unique audience total for the demographic in the report.
15 . A method comprising:
executing a machine learning model to generate a probability of an occurrence of a demographic classification;
generating, by executing an instruction with one or more processors, a coviewing factor based on panel data;
generating, by executing an instruction with the one or more processors, a viewer assignment output based on the coviewing factor;
determining, by executing an instruction with the one or more processors, a unique audience total based on the probability of the occurrence of the demographic classification;
adjusting, by executing an instruction with the one or more processors, the unique audience total based on a non-coverage factor; and
generating, by executing an instruction with the one or more processors, a report including the adjusted unique audience total.
16 . The method of claim 15 , wherein the machine learning model is trained using media tag impressions matched with panel members.
17 . The method of claim 15 , wherein the machine learning model is trained using media exposure data reformatted to match a format of a media tag impression.
18 . The method of claim 15 , further including generating the non-coverage factor by dividing a count of covered impressions to a count of measurable impressions, the covered impressions including impressions linked to a database proprietor home, the measurable impressions including the covered impressions and non-covered impressions, the non-covered impressions including impressions not linked to a database proprietor home, the count of the covered impressions and the count of the measurable impressions included in the viewer assignment output.
19 . The method of claim 18 , wherein the adjusting of the unique audience total includes:
aggregating a covered impressions total and a covered unique audience total from the viewer assignment output;
combining the non-coverage factor with the aggregated covered impressions and unique audience total;
deriving non-coverage frequency by dividing the covered impressions total by the covered unique audience total; and
adjusting the unique audience total by dividing the total impressions total by the non-coverage frequency.
20 . The method of claim 15 , further including:
matching identification data in a media tag with personal information; and
inputting the matched media tag into the machine learning model to generate the probability of the occurrence of the demographic classification.