Estimating reach and frequency of advertisements

Abstract

Estimating the reach and device frequency of a proposed advertising campaign based on the probability that advertising content delivery devices (e.g., a television set top box, radio) were used to deliver advertising content (e.g. television ad, radio ad) during specific time periods on specific delivery device channels.

1 . A computer-implemented method, comprising:
 accessing first probability data specifying first probabilities that viewing devices were used to present content on channels during time periods defined by time blocks;   accessing second probability data specifying second probabilities that the viewing devices were used to present the content in each time block in sets of two or more time blocks;   determining first number data for each time block specifying an estimated first number of the viewing devices used to present the content in the time block based on the first probabilities;   determining second number data for each set of two or more time blocks specifying an estimated second number of the viewing devices used to present the content in each time block in the set of two or more time blocks based on the second probabilities; and   generating impression overlap data for each set of two or more time blocks specifying an estimated impression overlap from viewing devices presenting the content in each of the time blocks in the set based on the first numbers of the viewing devices corresponding to the time blocks in the set, the second number of the viewing devices corresponding to the set and an estimated number of impressions for the content presented in the time blocks in the set.   
     
     
         2 . The method of  claim 1 , wherein the second probabilities are based on the first probabilities for the respective time blocks in the sets of two or more time blocks. 
     
     
         3 . The method of  claim 2 , wherein a second probability for a particular set of two or more time blocks is based on a product of the first probabilities for each of the time blocks in the particular set. 
     
     
         4 . The method of  claim 1 , wherein generating impression overlap data comprises:
 determining a ratio of the second number for a particular set of two or more time blocks to an aggregation of the first numbers for the time blocks in the particular set; and   determining an estimated impression overlap for the particular set based on a product of the ratio and the estimated number of impressions for the content presented in the time blocks in the particular set.   
     
     
         5 . The method of  claim 4 , further comprising:
 generating reach data specifying a reach of the content presented in the particular set of two or more time blocks based on a difference between the estimated number of impressions for the content presented in the time blocks in the particular set and the estimated impression overlap for the particular set.   
     
     
         6 . The method of  claim 5 , further comprising:
 generating device frequency data representing an estimated frequency with which the content will be presented in the time blocks in the particular set by use of a unique viewing device based on a ratio of the estimated number of impressions for the content presented in the time blocks in the particular set and the reach.   
     
     
         7 . The method of  claim 1 , wherein the content is a television advertisement. 
     
     
         8 . A system comprising:
 one or more processors; and   a computer-readable medium coupled to the one or more processors having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
 accessing first probability data specifying first probabilities that viewing devices were used to present content on channels during time periods defined by time blocks; 
 accessing second probability data specifying second probabilities that the viewing devices were used to present the content in each time block in sets of two or more time blocks; 
 determining first number data for each time block specifying an estimated first number of the viewing devices used to present the content in the time block based on the first probabilities; 
 determining second number data for each set of two or more time blocks specifying an estimated second number of the viewing devices used to present the content in each time block in the set of two or more time blocks based on the second probabilities; and 
 generating impression overlap data for each set of two or more time blocks specifying an estimated impression overlap from viewing devices presenting the content in each of the time blocks in the set based on the first numbers of the viewing devices corresponding to the time blocks in the set, the second number of the viewing devices corresponding to the set and an estimated number of impressions for the content presented in the time blocks in the set. 
   
     
     
         9 . The system of  claim 8 , wherein the second probabilities are based on the first probabilities for the respective time blocks in the sets of two or more time blocks. 
     
     
         10 . The system of  claim 9 , wherein a second probability for a particular set of two or more time blocks is based on a product of the first probabilities for each of the time blocks in the particular set. 
     
     
         11 . The system of  claim 8 , wherein generating impression overlap data comprises:
 determining a ratio of the second number for a particular set of two or more time blocks to an aggregation of the first numbers for the time blocks in the particular set; and   determining an estimated impression overlap for the particular set based on a product of the ratio and the estimated number of impressions for the content presented in the time blocks in the particular set.   
     
     
         12 . The system of  claim 11 , wherein the computer-readable medium comprises further instructions executable by the one or more processors and upon such execution cause the one or more processors to perform operations comprising:
 generating reach data specifying a reach of the content presented in the particular set of two or more time blocks based on a difference between the estimated number of impressions for the content presented in the time blocks in the particular set and the estimated impression overlap for the particular set.   
     
     
         13 . The system of  claim 12 , wherein the computer-readable medium comprises further instructions executable by the one or more processors and upon such execution cause the one or more processors to perform operations comprising:
 generating device frequency data representing an estimated frequency with which the content will be presented in the time blocks in the particular set by use of a unique viewing device based on a ratio of the estimated number of impressions for the content presented in the time blocks in the particular set and the reach.   
     
     
         14 . The system of  claim 8 , wherein the content is a television advertisement. 
     
     
         15 . Software stored in a computer readable medium and comprising instructions executable by a processing system and upon such execution cause the processing system to perform operations comprising:
 accessing first probability data specifying first probabilities that viewing devices were used to present content on channels during time periods defined by time blocks;   accessing second probability data specifying second probabilities that the viewing devices were used to present the content in each time block in sets of two or more time blocks;   determining first number data for each time block specifying an estimated first number of the viewing devices used to present the content in the time block based on the first probabilities;   determining second number data for each set of two or more time blocks specifying an estimated second number of the viewing devices used to present the content in each time block in the set of two or more time blocks based on the second probabilities; and   generating impression overlap data for each set of two or more time blocks specifying an estimated impression overlap from viewing devices presenting the content in each of the time blocks in the set based on the first numbers of the viewing devices corresponding to the time blocks in the set, the second number of the viewing devices corresponding to the set and an estimated number of impressions for the content presented in the time blocks in the set.   
     
     
         16 . The software of  claim 15 , wherein the second probabilities are based on the first probabilities for the respective time blocks in the sets of two or more time blocks. 
     
     
         17 . The software of  claim 16 , wherein a second probability for a particular set of two or more time blocks is based on a product of the first probabilities for each of the time blocks in the particular set. 
     
     
         18 . The software of  claim 15 , wherein generating impression overlap data comprises:
 determining a ratio of the second number for a particular set of two or more time blocks to an aggregation of the first numbers for the time blocks in the particular set; and   determining an estimated impression overlap for the particular set based on a product of the ratio and the estimated number of impressions for the content presented in the time blocks in the particular set.   
     
     
         19 . The software of  claim 18 , wherein the software comprises further instructions executable by the processing system and upon such execution cause the processing system to perform operations comprising:
 generating reach data specifying a reach of the content presented in the particular set of two or more time blocks based on a difference between the estimated number of impressions for the content presented in the time blocks in the particular set and the estimated impression overlap for the particular set.   
     
     
         20 . The software of  claim 19 , wherein the software comprises further instructions executable by the processing system and upon such execution cause the processing system to perform operations comprising:
 generating device frequency data representing an estimated frequency with which the content will be presented in the time blocks in the particular set by use of a unique viewing device based on a ratio of the estimated number of impressions for the content presented in the time blocks in the particular set and the reach.