Marketing Mix Modelling or MMM is a regression-based approach to identifying the drivers of sales for a business or brand – making it a form of attribution.  For many advertisers it is used to understand and optimise the effects of paid media in generating sales outcomes.  Unlike many other forms of attribution, MMM aims to measure the effects of both paid media and non-media sales drivers simultaneously.  This is important because it is only by accounting for the role of the non-media drivers that can we make more accurate statements about the performance of the media channels themselves. Without this delineation, we risk misattributing a sales effect to media when it might have been caused by something else. This in turn can cause an over statement of media’s performance.

With MMM models built, we are able to run scenarios and forecast outcomes from different types of media activity. This enables advertisers to optimise their media investments to maximise sales returns from media or marketing budgets invested.

Why is it called Marketing Mix Modelling?

MMM derives its name from the traditional ‘marketing mix’. The name recognises that all the variables in the marketing mix have a role in generating sales. So, let’s remind ourselves of the traditional marketing mix – the so called 4 Ps – Product, Price, Place and Promotion.

Product: In MMM, we might attach some attributes to the product – fast, smooth, light, powerful, low CO2 etc. These might be significant drivers within the category.

Price: Price is always a key determinant in consumer behaviour. As a general rule, products priced competitively sell more, and products priced less competitively relative to a category or competitors sell less. If we are to avoid confusing price effects with media effects, we naturally have to isolate the effect of price and take it out of the effectiveness equation.

Place: i.e. Distribution variables, whether they’re online (like delivery times) or offline (like store opening times) distribution variables usually have an effect on sales. If more stores are open, more product tends to be sold. If delivery times are long, versus competitors, less product tends to be sold. If we are to avoid confusing distribution effects with media effects, we also have to isolate the effect of distribution and take it out of the effectiveness equation.

Promotion: This variable is the promotional or advertising media spend variable. It can include advertising in media channels like TV, online display, search, social, OOH, cinema and print media.

What does an MM model actually look like?

This is a question many clients want to ask. MMM is often presented as a complex black box, when in fact it is simply an equation that captures the impact of the different elements of the marketing mix outlined above.  A Marketing Mix Model equation looks like this:

Sales = base (the levels of sales with no marketing) + (product attribute * a coefficient) + (price * a coefficient) + (distribution* a coefficient) + (promotion * a coefficient) + an error term.

Think of the coefficient is a statistically determined response rate which captures the rate at which sales are generated from changes in investments or activities in each of the Ps.

In statistics, the above might be written like this:

y = B0 + B1xX1 + B2xX2 + B3xX3 + error

How is MMM used to optimise paid media investments?

When we know the rate at which each “P” in our model generates sales, we can set values for each of the Ps excluding media advertising and then adjust the media advertising investment levels to see how those changes impact sales. This is a powerful tool in the marketer’s portfolio because it permits strong cases for media investment to be made. And that’s essential if to you want to maintain or secure increased budget from your CFO.