Methods and apparatus to incorporate saturation effects into marketing mix models

A non-transitory computer readable medium comprising instructions to reduce a computational burden on a machine used to generate a marketing mix model, the instructions, when executed, cause the machine to at least:

• convert adstock data associated with an advertising campaign into effective reached realized (ERR) data based on a relationship between reach and adstocked gross rating points indicative of saturation effects of the advertising campaign on a target audience of the advertising campaign, the adstock data corresponding to adstocked gross rating points generated from marketing mix input data, the marketing mix input data including (a) sales data associated with sales over a period of interest and (b) advertising data associated with the advertising campaign during the period of interest;
• and
• determine an impact of the advertising campaign on the sales during the period of interest based on a regression analysis of the ERR data relative to the sales data used to generate the marketing mix model, the computational burden on the machine reduced by eliminating tuning of response curves for the marketing mix model after the regression analysis.

A method to reduce a computational burden on a processor used to generate a marketing mix model, the method comprising:

• converting, via an instruction executed on the processor, adstock data associated with an advertising campaign into effective reached realized (ERR) data based on a relationship between reach and adstocked gross rating points indicative of saturation effects of the advertising campaign on a target audience of the advertising campaign, the adstock data corresponding to adstocked gross rating points generated from marketing mix input data, the marketing mix input data including (a) sales data associated with sales over a period of interest and (b) advertising data associated with the advertising campaign during the period of interest;
• and
• determining, via an instruction executed on the processor, an impact of the advertising campaign on the sales during the period of interest based on a regression analysis of the ERR data relative to the sales data used to generate the marketing mix model, the computational burden on the processor reduced by eliminating tuning of response curves for the marketing mix model after the regression analysis.