Main menu


MMM - What is Marketing Mix Modelling: marketing mix modelling example

Marketing Mix Modelling

What is the MMM? (Marketing Mix Modelling)

Market Mix Modeling (MMM) is a technique for quantifying the impact of various marketing inputs on sales or market share. MMM is used to determine how much each marketing input contributes to sales and how much to spend on each marketing input.

marketing mix,marketing mix definition,marketing mix 4p,marketing mix modelling,marketing mix 7p,marketing mix deutsch,marketing mix bedeutung,marketing mix definition deutsch,marketing mix example,marketing mix beispiel,marketing mix elements
marketing mix modelling in r

MMM assists in determining the effectiveness of each marketing input in terms of ROI. To put it another way, a marketing input with a higher return on investment (ROI) is more effective as a medium than one with a lower ROI.

MMM employs the Regression technique, and the results of the Regression analysis are then used to extract key information/insights.

Market Mix Modeling Concepts

In this article, I will discuss various concepts related to comprehending MMM.

1. Multi-Linear Regression (MLR)

As previously stated, Market Mix Modeling employs the Multi-Linear Regression principle. Sales or market share could be the dependent variable. Distribution, price, TV spends, outdoor campaign spends, newspaper and magazine spends, below-the-line promotional spends, and consumer promotions information are some of the independent variables that are commonly used. Some marketers now heavily rely on digital media to raise brand awareness. As a result, inputs such as digital spends, website visitors, and so on can also be used as inputs for MMM.

Between the dependent variables and predictors, an equation is formed. Depending on the relationship between the dependent variable and various marketing inputs, this equation could be linear or non-linear. Certain variables, such as television advertising, have a non-linear relationship with sales. This implies that an increase in TV GRP is not proportional to an increase in sales. In the following section, I will go over this in greater detail.

The betas produced by regression analysis aid in quantifying the impact of each input. Essentially, the beta depicts that increasing the input value by one unit increases the sales/profit by Beta units while keeping the other marketing inputs constant.

2. Predictors' Linear and Non-Linear Impact

Certain variables have a direct correlation with Sales. This means that as we increase these inputs, sales will continue to rise. However, variables such as TV GRP do not have a linear impact on sales. Increases in TV GRPs will only increase sales to a limited extent. Once that saturation point is reached, each additional unit of GRP will have less of an impact on sales. As a result, some transformations are performed on such non-linear variables in order to include them in linear models.

TV GRP is regarded as a non-linear variable because, according to marketers, an advertisement will only raise customer awareness to a certain extent. Customers who are already familiar with the brand would not benefit from additional exposure to advertisements after a certain point.

There are two parts to TV Adstock.

  • Diminishing Returns: The underlying principle of TV advertising is that exposure to TV ads creates awareness in the minds of customers to a certain extent. Beyond that, the impact of ad exposure begins to wane over time. Each additional GRP would have a lower impact on sales or awareness. As a result, the sales generated by incremental GRP begin to diminish and become constant. This effect is illustrated in the graph above, where the relationship between TV GRP and sales is non-linear. This type of relationship can be represented by taking the exponential or log of GRP.
  • Carry over effect or Decay Effect: Carry over effect refers to the impact of previous advertising on current sales. A small component known as lambda is multiplied by the previous month's GRP value. This component is also referred to as the Decay effect because the impact of previous months' advertisements diminishes over time.

3. Incremental and base sales:

Sales are divided into two components in Market Mix Modeling:
  • Base Sales: This is what marketers get if they do no advertising. It is sales as a result of the brand equity that has been built over time. Unless there is a change in economic or environmental factors, base sales are usually fixed.
  • Incremental Sales: Sales generated by marketing activities such as television advertisements, print advertisements, digital spends, promotions, and so on. To calculate contribution to total sales, total incremental sales are divided into sales from each input.

4. Contribution Diagrams

Contribution charts are the most straightforward way to represent sales as a result of each marketing input. Each marketing input's contribution is the product of its beta coefficient and input value.

5. Deep Dives

MMM results can be used to perform deep dive analysis in the future. Deep Dives can be used to evaluate the effectiveness of each campaign by determining which campaigns or creatives outperform the others. It can be used to perform copy analysis on creatives based on genre, language, channel, and so on.

Deep Dive insights are considered for budget optimization. To increase overall sales or market share, money is transferred from low-performing channels or genres to high-performing channels/genres.

6. Budget Management

Budget optimization is one of the most important decisions to make in any business for planning purposes. 

MMM assists marketers in optimizing future expenditures and increasing effectiveness. 

Using the MMM approach, it is determined which mediums perform better than others. The budget is then allocated by shifting money from low ROI mediums to high ROI mediums, maximizing sales while maintaining the budget constant.


table of contents title