Skip to main content

Marketing Mix Modeling (MMM): An Analytics Tool to Measure Advertising Effectiveness

How Marketing Mix Modeling Empowers CMOs to Overcome Annual Media Budget Challenges

One of the main challenges faced by Chief Marketing Officers (CMOs) is quantifying the impact of advertising on the business through various metrics. With the rise of the internet, the advertising landscape has become more hybrid, complex, and diverse, requiring new tools for measurement. The advantage of digital media is that they can be tracked, such as through "last click" attribution. However, these methods often overlook the effects that advertising may have before that last click. On the other hand, when we talk about offline media, advertising measurement is much more complex since its communication model, massive and unidirectional, prevents tracking of impacted users.

In this complex landscape, we need to develop new tools and techniques to guide our decision-making. Those who excel at analyzing the available information can implement the most effective advertising strategies. One of the best tools for understanding and processing all this data is Marketing Mix Modeling (MMM). This methodology uses advanced statistical models to determine the relationship between different business factors like advertising, price, distribution, sales, visits, and budgets. 

How do we apply Marketing Mix Modeling with Analytics?


The application of MMM models starts with understanding the business flow by analyzing the Customer Journey—the stages a customer goes through before buying a product or using a service. This analysis helps identify which steps in the funnel or process each business factor influences and determines the models needed to measure advertising impacts more accurately. These models follow a specific scheme (see Figure 1) that outlines the data required for their development. 

Figure 1: Example of a Modeling Scheme

Once the scheme is defined, the next phase is information gathering and data processing. This phase is critical in any Analytics project because the quality of the data directly impacts the quality of the analysis. Various data sources are collected and processed through ETL processes, which extract information from one or more sources to create an optimized database for developing relevant models.

These models are built around Key Performance Indicators (KPIs), which include all the variables needed to evaluate the effectiveness of a marketing strategy, such as sales, visits, and budget. The goal of MMM is to explain how KPIs behave in relation to different business factors. Regardless of the model used, the outcome is an equation that estimates the behavior of the analyzed variable. The closer this estimate is to reality, the stronger the model will be (see Figure 2). 

Figure 2: Example of Model Fitting

Once a reliable model is developed, it becomes possible to quantify the contribution of each business factor to sales, revenue, or the chosen response variable. A graphical representation (see Figure 3) can show how the contribution of the analyzed KPIs changes over time.

Figure 3: Example of Area Chart

Finally, these steps enable us to determine the impact of different marketing actions and calculate the Return on Investment (ROI) for each medium or advertising channel (see Figure 4). 

Figure 4: Representation of Advertising

What insights could we gain?
 

Models are not only useful for determining the contribution of various business factors, but they also allow us to:

  • Measure the relationships between different steps in the modeled Customer Journey. Understand how competitors' actions affect the business.
  • Analyze the impact of marketing investments in different advertising campaigns.
  • Determine the short- and long-term effectiveness of advertising actions. Identify potential synergies between media that enhance their effectiveness.
  • Estimate nonlinear behaviors of media, their saturation levels, and create scenarios to optimize media strategy based on budgets.
  • Make predictions and set business objectives.


Why implement MMM models?

Advertisers often ask about the return on investment when considering a Marketing Mix Modeling project. Do these models provide benefits that justify the cost of developing them?

To answer this, we analyzed results from our benchmark, which includes over 100 media mix optimization exercises conducted in recent years (see Figure 5). In more than half of the cases, with the same advertising budget, the contribution to the business increased by over 6%. 

Figure 5: Deloitte Benchmark Estimated Increase in Advertising Effectiveness after Optimization

Beyond the clear improvements in advertising effectiveness, it's important to note that these models also provide insights into various actionable levers, offering opportunities for improvement across different areas. The many insights gained through MMM make it a valuable tool for strategic decision-making.


Ready to take your advertising strategy to the next level with actionable insights from Marketing Mix Modeling?

Our team of experts is here to help you optimize your media investments, drive better results, and make data-driven decisions. Contact us today to learn how we can tailor an MMM solution to meet your business needs. Let’s turn your data into powerful results—reach out to us now!  

Did you find this useful?

Thanks for your feedback

If you would like to help improve Deloitte.com further, please complete a 3-minute survey