Methods and apparatus to incorporate saturation effects into marketing mix models
Methods and apparatus to incorporate saturation effects into marketing mix models are disclosed. An example apparatus includes means for converting adstock data associated with an advertising campaign into effective reached realized (ERR) data based on a first saturation curve, the adstock data corresponding to adstocked gross rating points generated from marketing mix input data. The apparatus further including means for performing regression analysis to: identify the first saturation curve from among a plurality of plausible curves based on a fit of different ones of the plurality of plausible curves to the marketing mix input data, the first saturation curve to define a relationship indicative of saturation effects of the advertising campaign on a target audience of the advertising campaign; and determine an impact of the advertising campaign on sales during a period of interest based on a regression analysis of the ERR data relative to sales data.
1. An apparatus to reduce a computational burden on a processor used to generate a marketing mix model, the apparatus comprising:
means for converting adstock data associated with an advertising campaign into effective reached realized (ERR) data based on a first saturation curve, the adstock data corresponding to adstocked gross rating points generated from marketing mix input data; and
means for performing regression analysis to:
identify the first saturation curve from among a plurality of plausible curves based on a fit of different ones of the plurality of plausible curves to the marketing mix input data, the first saturation curve to define a relationship indicative of saturation effects of the advertising campaign on a target audience of the advertising campaign; and
determine an impact of the advertising campaign on sales during a period of interest based on a regression analysis of the ERR data relative to sales data included in the marketing mix input data, the sales data used to generate the marketing mix model, the computational burden on the processor reduced by incorporation of the saturation effects of the advertising campaign into the regression analysis, the incorporation of the saturation effects based on the converting of the adstock data into the ERR data using the first saturation curve.
2. The apparatus as defined in claim 1 , wherein the ERR data is indicative of a percentage of the target audience that experienced effective exposure to an advertisement of the advertising campaign during a first segment of time in the period of interest an average number of instances sufficient to elicit a response to the advertisement, the effective exposure including actual exposure to the advertisement during the first segment of time and a time lagged effect of actual exposure to the advertisement during previous segments of time prior to the first segment of time.
3. The apparatus as defined in claim 1 , further including means for storing the plurality of plausible curves, the relationship determined by looking up ones of the plurality of plausible curves in the storing means.
4. The apparatus as defined in claim 1 , further including means for calculating the plurality of plausible curves based on a range of plausible penetrations and a range of plausible effective frequencies, ones of the plausible curves corresponding to (a) ones of the plausible penetrations and (b) ones of the plausible effective frequencies.
5. The apparatus as defined in claim 4 , wherein the range of plausible penetrations and the range of plausible effective frequencies are to be determined based on an estimate of (a) an initial penetration and (b) an initial effective frequency.
6. The apparatus as defined in claim 5 , wherein the estimate is to be based on audience measurement data including (a) demographic information corresponding to the target audience of the advertising campaign and (b) media type information corresponding to a type of media associated with the advertising campaign.
7. The apparatus as defined in claim 5 , wherein the estimate is to be based on at least one of a geographic region associated with the advertising campaign, a type of product or service associated with the advertising campaign, a comparable penetration associated with a comparable campaign for related or competing products, a comparable effective frequency associated with the comparable campaign, or a complexity of the advertising campaign.
8. The apparatus as defined in claim 5 , wherein the estimate is to be based on a prior saturation curve corresponding to a previously analyzed advertising campaign.
9. The apparatus as defined in claim 5 , further including means for simulating an advertising campaign to:
generate a simulated advertising campaign based on ones of the plausible penetrations and ones of the effective frequencies; and
determine data points indicative of simulated reach corresponding to simulated gross rating points associated with the simulated advertising campaign, wherein the calculating means is to calculate corresponding ones of the plurality of plausible curves that fit the data points.
10. An apparatus to reduce a computational burden on a processor used to generate a marketing mix model, the apparatus comprising:
a reach calculator to convert adstock data associated with an advertising campaign into effective reached realized (ERR) data based on a first saturation curve, the adstock data corresponding to adstocked gross rating points generated from marketing mix input data; and
a regression engine to:
identify the first saturation curve from among a plurality of plausible curves based on a fit of different ones of the plurality of plausible curves to the marketing mix input data, the first saturation curve to define a relationship indicative of saturation effects of the advertising campaign on a target audience of the advertising campaign; and
determine an impact of the advertising campaign on sales during a period of interest based on a regression analysis of the ERR data relative to sales data included in the marketing mix input data, the sales data used to generate the marketing mix model, the computational burden on the processor reduced by incorporation of the saturation effects of the advertising campaign into the regression analysis, the incorporation of the saturation effects based on the converting of the adstock data into the ERR data using the first saturation curve, at least one of the reach calculator or the regression engine implemented by the processor.
11. The apparatus as defined in claim 10 , wherein the ERR data is indicative of a percentage of the target audience that experienced effective exposure to an advertisement of the advertising campaign during a first segment of time in the period of interest an average number of instances sufficient to elicit a response to the advertisement, the effective exposure including actual exposure to the advertisement during the first segment of time and a time lagged effect of actual exposure to the advertisement during previous segments of time prior to the first segment of time.
12. The apparatus as defined in claim 10 , further including a database to store the plurality of plausible curves, the relationship determined by looking up ones of the plurality of plausible curves in the database.
13. The apparatus as defined in claim 10 , further including a saturation curve calculator to calculate the plurality of plausible curves based on a range of plausible penetrations and a range of plausible effective frequencies, ones of the plausible curves corresponding to (a) ones of the plausible penetrations and (b) ones of the plausible effective frequencies.
14. The apparatus as defined in claim 13 , wherein the range of plausible penetrations and the range of plausible effective frequencies are to be determined based on an estimate of (a) an initial penetration and (b) an initial effective frequency.
15. The apparatus as defined in claim 14 , wherein the estimate is to be based on audience measurement data including (a) demographic information corresponding to the target audience of the advertising campaign and (b) media type information corresponding to a type of media associated with the advertising campaign.
16. An apparatus to reduce a computational burden on processor circuitry used to generate a marketing mix model, the apparatus comprising:
at least one memory;
computer readable instructions; and
the processor circuitry to execute the computer readable instructions to at least:
convert adstock data associated with an advertising campaign into effective reached realized (ERR) data based on a first saturation curve, the adstock data corresponding to adstocked gross rating points generated from marketing mix input data;
identify the first saturation curve from among a plurality of plausible curves based on a fit of different ones of the plurality of plausible curves to the marketing mix input data, the first saturation curve to define a relationship indicative of saturation effects of the advertising campaign on a target audience of the advertising campaign; and
determine an impact of the advertising campaign on sales during a period of interest based on a regression analysis of the ERR data relative to sales data included in the marketing mix input data, the sales data used to generate the marketing mix model, the computational burden on the processor circuitry reduced by incorporation of the saturation effects of the advertising campaign into the regression analysis, the incorporation of the saturation effects based on the converting of the adstock data into the ERR data using the first saturation curve.
17. The apparatus as defined in claim 16 , wherein the ERR data is indicative of a percentage of the target audience that experienced effective exposure to an advertisement of the advertising campaign during a first segment of time in the period of interest an average number of instances sufficient to elicit a response to the advertisement, the effective exposure including actual exposure to the advertisement during the first segment of time and a time lagged effect of actual exposure to the advertisement during previous segments of time prior to the first segment of time.
18. The apparatus as defined in claim 16 , wherein the processor circuitry is to calculate the plurality of plausible curves based on a range of plausible penetrations and a range of plausible effective frequencies, ones of the plausible curves corresponding to (a) ones of the plausible penetrations and (b) ones of the plausible effective frequencies.
19. The apparatus as defined in claim 18 , wherein the range of plausible penetrations and the range of plausible effective frequencies are to be determined based on an estimate of (a) an initial penetration and (b) an initial effective frequency.
20. The apparatus as defined in claim 19 , wherein the estimate is to be based on audience measurement data including (a) demographic information corresponding to the target audience of the advertising campaign and (b) media type information corresponding to a type of media associated with the advertising campaign.
21. The apparatus as defined in claim 19 , wherein the estimate is to be based on at least one of a geographic region associated with the advertising campaign, a type of product or service associated with the advertising campaign, a comparable penetration associated with a comparable campaign for related or competing products, a comparable effective frequency associated with the comparable campaign, or a complexity of the advertising campaign.
22. The apparatus as defined in claim 19 , wherein the estimate is to be based on a prior saturation curve corresponding to a previously analyzed advertising campaign.
23. The apparatus as defined in claim 19 , wherein the processor circuitry is to:
generate a simulated advertising campaign based on ones of the plausible penetrations and ones of the effective frequencies;
determine data points indicative of simulated reach corresponding to simulated gross rating points associated with the simulated advertising campaign; and
calculate corresponding ones of the plurality of plausible curves that fit the data points.
24. The apparatus as defined in claim 16 , wherein the processor circuitry is to store the plurality of plausible curves in a database, the relationship determined by looking up ones of the plurality of plausible curves in the database.
25. The apparatus as defined in claim 14 , wherein the estimate is to be based on at least one of a geographic region associated with the advertising campaign, a type of product or service associated with the advertising campaign, a comparable penetration associated with a comparable campaign for related or competing products, a comparable effective frequency associated with the comparable campaign, or a complexity of the advertising campaign.
26. The apparatus as defined in claim 14 , wherein the estimate is to be based on a prior saturation curve corresponding to a previously analyzed advertising campaign.
27. The apparatus as defined in claim 14 , further including a marketing simulator to:
generate a simulated advertising campaign based on ones of the plausible penetrations and ones of the effective frequencies; and
determine data points indicative of simulated reach corresponding to simulated gross rating points associated with the simulated advertising campaign, wherein the saturation curve calculator is to calculate corresponding ones of the plurality of plausible curves that fit the data points.