Marketing Mix Modelling or Attribution Modelling. Which one is for you?


If you are an avid reader of this blog, you most probably know what attribution modelling is.

I have written dozens of articles on Attribution Modelling on this blog.

But do you know what ‘Marketing Mix Modelling’ is and is it same or different than ‘Attribution Modelling’?

Introduction to Marketing Mix Modelling

Marketing mix modelling (MMM) is a set of statistical analysis techniques which are used to measure and forecast the impact of various marketing activities on sales and ROI.

It is used to measure the overall marketing effectiveness and determine optimal ad spend among various marketing channels.

The word ‘mix’ in MMM refers to the mix of the 4Ps of marketing (Product, Price, Place and Promotion).

In MMM, we carry out data analysis with the aim to understand and find the optimal mix of these 4Ps.

Regression analysis is also carried out to forecast the impact of various marketing activities on sales.

A marketing mix model can be made of following types of data:

  • Target Audience data
  • Product data (product price, product features)
  • Competitive data
  • Industry data
  • Economic data
  • Marketing data
  • Conversion data (sales, profit, ROI)

Get the Free E-Book (52 Pages)

The Difference between Attribution Modelling and Marketing Mix Modelling

Attribution Modellingcan be considered as a subset of MMM where the focus is on understanding and finding the optimal mix of ‘digital’ marketing channels.

Pay special attention to the word ‘Digital’ here. 

We use attribution models to measure and understand the impact of digital marketing touch points in a conversion path and to determine most effective marketing channels for investment.

So in the context of digital media, Marketing mix modelling can be referred to as ‘Attribution Modelling’.

However unlike MMM, implementing attribution modelling is pretty lightweight, in the sense that it usually does not involve direct and heavy use of statistics by an ‘end user’.

Whatever statistical analysis that is carried out, is by the attribution model itself.

So you don’t need a master’s degree in statistics to implement attribution modelling.  

This is one advantage of attribution modelling over MMM.

The other advantage is that, since you do not heavily use statistics to create attribution models, your models are less prone to statistical errors (as long as you use high quality data to feed your models).

Why Do You Need Attribution Modelling?

You may be wondering at this point that, Marketing Mix Modelling has been around for decades and sound very much like ‘Attribution Modelling’.

Then why do we need attribution modelling?

Why not just use ‘Marketing Mix Modelling’?

The problem with MMM is that, it is much older than the internet itself.

The concept was first introduced when there were was no digital media, no search engines, no web browsers.

And somehow it just couldn’t catch up with the digital age.

Now I am not implying that MMM is an outdated set of techniques.

It is still very much relevant and has its own place.

It just doesn’t work well when it comes to digital marketing mix modelling.

Unlike MMM, attribution modelling provides much more control over optimizing various digital marketing channels for ROI.

This level of control comes because of the immediate and real time access to digital data at an individual user level. 

Unlike MMM models, attribution models natively integrate with your web analytics data.

For example the attribution models provided by Google Analytics natively integrate with GA.

The ‘Data Driven Attribution (DDA) Model’ provided by GA can be integrated with several Google and non Google digital data sources.

For example, DDA model can integrated with: Doubleclick Campaign Manager, Google Adwords, Google Search Console, Google play, Google Bigquery etc in addition to Google Analytics.

Such type of integration make it possible for attribution models, to access users’ data in real time which makes attribution modelling much more accurate and accountable.

MMM models are often built on outdated and highly aggregated data.

The data is outdated in comparison to the real time data which feeds an attribution model esp. algorithmic attribution models (like Data Driven Attribution Model).

As such, a traditional MMM model is not suitable for carrying out digital marketing mix modelling aka attribution modelling.


Attribution Modelling in Google Ads and FacebookAttribution Modelling in Google Analytics and Beyond

Get my best selling books on Attribution Modelling

  • Learn to implement attribution modelling in your organisation
  • Understand the customer purchase journey across devices
  • Determine the most effective marketing channels for investment

 Click book covers to find out more

Integrating Attribution Modelling into Marketing Mix Modelling

If your business has both online and offline presence and you carry out both online and offline marketing then you are an ideal candidate for integrating Attribution Modelling into MMM.

For example if you are retailer who has got both physical and online stores and you are actively involved in both online and offline advertising then you are an ideal candidate for implementing both MMM and attribution modelling.

The main advantage of Attribution Modelling and MMM integration is that, you can feed the attribution modelling data to your MMM model and can more accurately measure the overall marketing effectiveness.

You can also more accurately forecast the impact of both online and offline marketing activities on sales and ROI.

Remember, true multi channel analytics is nonline i.e. it is neither purely online nor purely offline.

So we can’t afford to measure online and offline customers purchase journeys in silos.

We need to learn to understand the complete customer purchase journey which takes both online and offline touchpoints into account.

We now know that, both online and offline marketing campaigns and touchpoints impact each other.

We also know that, in the world of multi channel marketing, no single marketing channel is solely responsible for generating sales.

Different marketing channels work together to create sales and conversions. 

So in order to truly understand the overall marketing performance, we need to take both online and offline marketing touchpoints into account.

Other articles on Attribution Modelling in Google Analytics

  1. Touch Point Analysis in Google Analytics Attribution Modelling
  2. 8 Google Analytics Conversions Segments You Must Use
  3. Default and Custom Attribution Models in Google Analytics
  4. Attribution Model Comparison Tool in Google Analytics
  5. Which Attribution Model to use in Google Analytics?
  6. How to create Custom Attribution Model in Google Analytics

  1. How to do ROI Analysis in Google Analytics
  2. Google Analytics Attribution Modelling – Complete Guide
  3. Guide to Data Driven Attribution Model in Google Analytics
  4. Conversion Credit distribution for Attribution Models in Google Analytics
  5. You are doing Google Analytics all wrong. Here is why

  1. Marketing Mix Modelling or Attribution Modelling. Which one is for you?
  2. Introduction to Nonline Analytics – True Multi Channel Analytics
  3. How to set up Data driven attribution model in Google Analytics
  4. How to valuate Display Advertising through Attribution Modelling
  5. Understanding Shopping Carts for Analytics and Conversion Optimization

  1. View-through conversion tracking in Google Analytics
  2. Understanding Missing Touch Points in Attribution Modelling
  3. Guide to Offline Conversion Tracking in Google Analytics
  4. How to explain attribution modelling to your clients
  5. 6 Keys to Digital Success in Attribution Modelling

  1. How to use ZMOT to increase Conversions and Sales exponentially
  2. How to Measure and Improve the Quality of SEO Traffic through Google Analytics
  3. How to analyse and report the true value of your SEO Campaign
  4. How to allocate Budgets in Multi Channel Marketing
  5. What You Should Know about Historical Data in Web Analytics

  1. Google Analytics Not Provided Keywords and how to unlock and analyze them
  2. Selecting the Best Attribution Model for Inbound Marketing
  3. Introduction to TV attribution in Google Analytics Attribution 360
  4. Cross Device Reports in Google Analytics via Google Signals
  5. Data-Driven Attribution Model Explorer in Google Analytics
  6. What is Attribution Modelling and why it is the ‘key’ to online business success?
  7. How Does Attribution Work?
  8. How is Attribution Modelling helpful for e-commerce and non-e-commerce websites?

Most Popular E-Books from OptimizeSmart

Learn to read e-commerce reports book banner

How to learn and master Web Analytics and Google Analytics?

Take the Course

Check out my best selling books on Web Analytics and Conversion Optimization on Amazon

How to get lot more useful information?

I share lot more useful information on Web Analytics and Google Analytics on LinkedIn then I can via any other medium. So there is really an incentive for you, to follow me there.

Himanshu Sharma

Certified web analyst and founder of

My name is Himanshu Sharma and I help businesses find and fix their Google Analytics and conversion issues. If you have any questions or comments please contact me.

  • Over twelve years' experience in SEO, PPC and web analytics
  • Google Analytics certified
  • Google AdWords certified
  • Nominated for Digital Analytics Association Award for Excellence
  • Bachelors degree in Internet Science
  • Founder of and

I am also the author of four books:

error: Alert: Content is protected !!