Cross-media campaigns with bias adjustment and attribution modeling

Abstract

A method for determining advertising effectiveness of cross-media campaigns provided. The effectiveness of the combined campaign is plotted, and the effects of different media are isolated. Examining complementary effects and synergies are examined, and a dollar-for-dollar comparison for each of the media is performed. This dollar-for-dollar comparison may include a return on marketing objective calculation. If applicable, budget re-allocations are recommended. Optionally, post effectiveness, efficiency, and allocation analysis are performed. Such analysis may include providing descriptive advertising and media suggestions on each media independently.

1 - 4 . (canceled) 
     
     
         5 . A method of conducting and measuring a cross-media campaign, comprising:
 delivering, through two or more media, advertising to members of a population, wherein at least one of the media is an online medium;   assigning members of the population into one or more exposed groups or one or more control groups, wherein assigning members to at least one of the exposed groups and at least one of the control groups comprises adjusting for bias from variations in usage levels among members of the population for at least one of the media;   determining, by a computer system, one or more measures of effectiveness of at least one of the two or more media in the cross-media campaign, wherein determining the one or more measures of effectiveness of at least one of the media comprises determining an incremental effect on sales or an incremental branding effect of one of the media; and   isolating an effect of at least one of the media from the effects of at least one of the other media.   
     
     
         6 . The method of  claim 5 , wherein adjusting for bias comprises adjusting for heavier use of at least one media by some of the members of the population. 
     
     
         7 . The method of  claim 5 , wherein adjusting for bias comprises adjusting for heavier use of an online medium by some of the members of the population. 
     
     
         8 . The method of  claim 5 , further comprising frequency capping at least survey participant to address usage bias in the population for at least one of the media. 
     
     
         9 . The method of  claim 5 , further comprising removing at least one contaminated respondent from at least one of the groups. 
     
     
         10 . The method of  claim 5 , further comprising weighting one or more groups or members of the population to address usage bias in the population for at least one of the media. 
     
     
         11 . The method of  claim 5 , wherein determining the one or more measures of effectiveness of at least one of the media comprises determining an incremental impact on sales of one of the media. 
     
     
         12 . The method of  claim 5 , wherein determining the one or more measures of effectiveness of at least one of the media comprises determining an incremental branding effect of one of the media. 
     
     
         13 . The method of  claim 5 , wherein determining the one or more measures of effectiveness of at least one of the media comprises determining an incremental effect on sales and an incremental branding effect of one of the media. 
     
     
         14 . The method of  claim 5 , wherein determining the one or more measures of effectiveness of at least one of the two or more media comprises oversampling for at least one of the two or more media, wherein the oversampling comprises measuring one or more members of the population pre and post event. 
     
     
         15 . The method of  claim 5 , wherein determining the one or more measures of effectiveness of at least one of the two or more media comprises continuous tracking of at least one of the media to measure at least one market change from pre event to post event. 
     
     
         16 . The method of  claim 5 , wherein at least one of the members of at least one of the groups is not randomly selected. 
     
     
         17 . The method of  claim 5 , wherein determining the one or more measures of effectiveness of at least one of the two or more media comprises applying at least one statistical model to determine the contribution of at least one of the media to the campaign. 
     
     
         18 . The method of  claim 5 , wherein determining the one or more measures of effectiveness of at least one of the two or more media comprises applying a moving average trend line for at least one local market. 
     
     
         19 . The method of  claim 5 , further comprising displaying, for each of at least one of the two or more media, an effect of the medium. 
     
     
         20 . A method of conducting and measuring a cross-media campaign, comprising:
 delivering, through two or more media, advertising to members of a population, wherein at least one of the media is an online medium;   assigning members of the population into one or more exposed groups or one or more control groups;   determining, by a computer system, one or more measures of effectiveness of at least one of the two or more media in the cross-media campaign, wherein determining the one or more measures of effectiveness of at least one of the two or more media comprises applying one or more statistical models to determine the contribution to sales of at least one of the media in the campaign, and wherein determining the one or more measures of effectiveness of at least one of the media comprises determining an incremental effect on sales or an incremental branding effect of one of the media; and   isolating an effect of at least one of the media from the effects of at least one of the other media.   
     
     
         21 . The method of  claim 20 , wherein at least one of the statistical models comprises a moving average analysis, wherein determining the one or more measures of effectiveness of at least one of the two or more media comprises applying a moving average trend line for at least one local market. 
     
     
         22 . The method of  claim 20 , further comprising weighting one or more groups or members of the population to address usage bias in the population for at least one of the media. 
     
     
         23 . The method of  claim 20 , wherein determining the one or more measures of effectiveness of at least one of the two or more media comprises oversampling for at least one of the two or more media, wherein the oversampling comprises measuring one or more members of the population pre and post event. 
     
     
         24 . The method of  claim 20 , wherein determining the one or more measures of effectiveness of at least one of the two or more media comprises continuous tracking of at least one of the media to measure at least one market change from pre event to post event.