System and method for tracking advertiser return on investment using set top box data

1. A method comprising:

receiving, by a processing device over a network, set-top box data for a plurality of set-top boxes, sales data identifying a plurality of purchasers of a product or service; and advertising data identifying advertisement placement history for an advertisement campaign for the product or service;

associating the plurality of set-top boxes with a plurality of viewers; receiving, by the processing device over the network, consumer enrichment data including, for each person among a plurality of persons, demographic data, behavior data, and psychographics data, the plurality of viewers being among the plurality of persons;

enriching the set-top box data with the consumer enrichment data; enriching the sales data with the consumer enrichment data, setting a time window associated with a portion of each media instance on which the advertisement campaign was presented based on a predetermined time window size, the time window size being greater than the duration of the advertisement; and determining whether an individual viewer of the plurality of viewers viewed the media instance for at least a threshold percentage of the time window based on set-top box data for a set-top box of the plurality of set-top boxes associated with the individual viewer;

upon determining that the individual viewer viewed the media instance for at least the threshold percentage of the time window, identifying a single advertising exposure event for the individual viewer;

calculating, for each viewer of the plurality of viewers, an advertising weight as a function of a number of exposures of the advertisement as applied to the viewer based on the advertising exposure events;

calculating, for each viewer, a score representing a degree-of-targetedness between a target for the advertisement campaign and the viewer, wherein the degree-of-targetedness is calculated by generating a first multi-dimensional vector based on the consumer enrichment data for the individual viewer, generating a second multidimensional vector based on consumer enrichment data for buyers of the product or service, and calculating a difference between the first multi-dimensional vector and the second multi-dimensional vector;

managing the advertisement campaign based on the advertising weight and the degree-of-targetedness;

generating a multi-dimensional model of advertising effectiveness that models combined effects of the advertising weight and the degree of targetedness based on a combination of computed advertising weights and degrees of targetedness for the plurality of viewers; and

applying the multi-dimensional model to the received set-top box data and the received sales data to track a number of sales attributable to the advertisement campaign.

2. The method of claim 1 , wherein associating the plurality of set-top boxes with the plurality of viewers comprises:

associating each set-top box of the plurality of set-top boxes with a household of a plurality of households based on billing or subscription records of a person who is paying for a television service provided by one of the plurality of set-top boxes; and

associating each household of the plurality of households with additional persons in the household based on third party data about the additional persons residing within the household.

3. The method of claim 1 , wherein the degree of targetedness is further calculated by measuring the probability that an individual exposed to the advertisement campaign will purchase the product or service, and wherein determining the degree of targetedness as applied to an individual viewer comprises:

identifying programs viewed by the individual viewer;

determining a first quantity of individual viewers that viewed the programs;

determining a second quantity of the individual viewers that also purchased the product or service; and

dividing the second quantity by the first quantity.

4. The method of claim 1 , further comprising:

determining a total number of purchasers of the product or service;

measuring a number of the purchasers who viewed at least one advertisement of the advertisement campaign; and

reporting the number of the purchasers who viewed at least one advertisement based on time.

5. The method of claim 1 , wherein the demographic targeting metric is based on a probability of a conversion for the product or service from a media instance on which the advertisement campaign was presented.

6. A tangible, non-transitory computer readable storage medium having instructions that, when executed by a processing device, cause the processing device to perform operations comprising:

receiving, by the processing device over a network, set-top box data for a plurality of set-top boxes, sales data identifying a plurality of purchasers of a product or service, and advertising data identifying advertisement placement history for an advertisement campaign for the product or service;

associating the plurality of set-top boxes with a plurality of viewers;

receiving, by the processing device over the network, consumer enrichment data including, for each person among a plurality of persons, demographic data, behavior data, and psychographics data, the plurality of viewers being among the plurality of persons;

enriching the set-top box data with the consumer enrichment data; enriching the sales data with the consumer enrichment data, setting a time window associated with a portion of each media instance on which the advertisement campaign was presented based on a predetermined time window size, the time window size being greater than the duration of the advertisement; and determining whether an individual viewer of the plurality of viewers viewed the media instance for at least a threshold percentage of the time window based on set-top box data for a set-top box of the plurality of set-top boxes associated with the individual viewer;

upon determining that the individual viewer viewed the media instance for at least the threshold percentage of the time window, identifying a single advertising exposure event for the individual viewer;

calculating, for each viewer of the plurality of viewers, an advertising weight as a function of a number of exposures of the advertisement as applied to the viewer based on the advertising exposure events;

calculating, for each viewer, a score representing a degree-of-targetedness between the advertisement campaign and the viewer, wherein the degree-of-targetedness is calculated by generating a first multi-dimensional vector based on the consumer enrichment data for the individual viewer, generating a second multi-dimensional vector based on consumer enrichment data for buyers of the product or service, and calculating a difference between the first multi-dimensional vector and the second multi-dimensional vector; and

managing the advertisement campaign based on the advertising weight and the degree-of-targetedness;

generating a multi-dimensional model of advertising effectiveness that models combined effects of the advertising weight and the degree of targetedness for a combination of computer advertising weights and degrees of targetedness for the plurality of viewer; and

applying the multi-dimensional model to the received set-top box data and the received sales data to track a number of sales attributable to the advertisement campaign.

7. The tangible, non-transitory computer readable storage medium of claim 6 , wherein associating the plurality of set-top boxes with the plurality of viewers comprises:

associating each set-top box of the plurality of set-top boxes with a household of a plurality of households based on billing or subscription records of a person who is paying for a television service provided by one of the plurality of set-top boxes;

and associating each household of the plurality of households with additional persons in the household based on third party data about the additional persons residing within the household.

8. The tangible, non-transitory computer readable storage medium of claim 6 , wherein generating the multi-dimensional model comprises:

determining an effect that the advertising weight of the advertisement has on sales metrics identified from the sales data; and

determining an effect that the degree of targetedness for the advertisement has on the sales metrics.

9. The tangible, non-transitory computer readable storage medium of claim 6 , the operations further comprising:

using the multi-dimensional model to predict a number of conversions for a particular advertisement weight applied to a program having a particular degree of targetedness.

10. The tangible, non-transitory computer readable storage medium of claim 6 , wherein determining an advertising weight as applied to an individual viewer comprises:

receiving programming guide data;

analyzing the set-top box data and combining with the programming guide data to determine programs watched by the individual viewer over a time period;

calculating the advertising exposure events for the individual viewer by further combining the advertising data to the combined viewing data and programming data; and

aggregating the advertising exposure events for the individual viewer.

11. The tangible, non-transitory computer readable storage medium of claim 6 , wherein the degree of targetedness is further calculated at least in part by measuring the probability that an individual exposed to the advertisement campaign will purchase the product or service, and wherein determining the degree of targetedness as applied to an individual viewer comprises:

identifying programs viewed by the individual viewer;

determining a first quantity of individual viewers that viewed the programs;

determining a second quantity of the individual viewers that also purchased the product or service; and

dividing the second quantity by the first quantity.

12. The tangible, non-transitory computer readable storage medium of claim 6 , the operations further comprising:

determining a total number of purchasers of the product or service; measuring a number of the purchasers who viewed at least one advertisement of the advertisement campaign; and

reporting the number of the purchasers who viewed at least one advertisement based on time.

13. A computing device comprising:

a memory; and

a processing device coupled to the memory, the processing device to: receive, over a network, set-top box data for a plurality of set-top boxes, sales data identifying a plurality of purchasers of a product or service, and advertising data identifying advertisement placement history for an advertisement campaign for the product or service;

associate the plurality of set-top boxes with a plurality of viewers;

receive, over the network, consumer enrichment data including, for each person among a plurality of persons, demographic data, behavior data, and psychographics data, the plurality of viewers being among the plurality of persons;

enrich the set-top box data with the consumer enrichment data;

enrich the sales data with the consumer enrichment data,

set a time window associated with a portion of each media instance on which the advertisement campaign was presented based on a predetermined time window size, the time window size being greater than the duration of the advertisement; and

determine whether an individual viewer of the plurality of viewers viewed the media instance for at least a threshold percentage of the time window based on set-top box data for a set-top box of the plurality of set-top boxes associated with the individual viewer;

upon determining that the individual viewer viewed the media instance for at least the threshold percentage of the time window, identify a single advertising exposure event for the individual viewer;

calculate, for each viewer of the plurality of viewers, an advertising weight as a function of a number of exposures of the advertisement as applied to the viewer based on the advertising exposure events;

calculate, for each viewer, a score representing a degree-of-targetedness between the advertisement campaign and the viewer, wherein the degree-of-targetedness is calculated by generating a first multi-dimensional vector based on the consumer enrichment data for the individual viewer; generating a second multidimensional vector based on consumer enrichment data for buyers of the product or service, and calculating a difference between the first multi-dimensional vector and the second multi-dimensional vector; and

manage the advertisement campaign based on the advertising weight and the degree-of-targetedness;

generating a multi-dimensional model of advertising effectiveness that models the plurality of viewers; and

applying the multi-dimensional model to the received set-top box data and the received sales data to track a number of sales attributable to the advertisement campaign.