In this article, we’re going to show you how Marketing Mix Modelling (MMM) works, why it’s needed, plus the pros and cons of using it to assess your marketing efforts. Then, as a bonus, we’re going to provide you with an alternative method to tie sales revenue directly to your online and offline channels.
If you’ve been looking for a straightforward guide to Marketing Mix Modelling (designed for marketers) then this is for you.
Marketing Mix Modelling is a complex topic.
Having a solid grasp of statistics and data science will help you make the most of it, but the underlying concepts are simple:
- Is your marketing working?
- Which channels have the best ROI?
- Is your increase in sales coming from marketing?
- Are there other reasons for your successes or failures?
84% of marketers say relating conversions to marketing is very important to growth, but only 10% have a “strong capability” to do so.
On that note, let’s jump straight into this article, and start by looking at what Marketing Mix Modelling is.
FYI: This is a beginners guide for marketers who want to cover the basics of Marketing Mix Modelling. If you’re looking for something a little more analytical, I’d recommend watching this video by Lenskhold Group.
What is Marketing Mix Modelling?
Marketing Mix Modelling, or MMM, is the act of taking any activities that could influence sales numbers, then applying statistical modelling to show how marketing contributes to changes in sales volume.
MMM breaks down your results by channel.
So, you can see which marketing activities are having the most significant impact on your ROI.
Why is Marketing Mix Modelling Used?
You know what it feels like to put together a report for your Head of Marketing, CEO, or investors.
It’s hard work.
You need precise data so that you can justify your conclusions and prove why you deserve a bigger marketing budget.
Marketing Mix Modelling combines all of your activities and shows the effect it’s having on your revenue.
This could span from an offline campaign promoting a half price sale, or a piece of content that went viral on Facebook.
MMM enables you to track elements such as:
- Traffic attributed to it
- Conversion rates
- Sales numbers
When your Marketing Mix Modelling is done, you’ll have your data linking your sales back to your marketing efforts.
You’ll gain a clear picture of your marketing wins (and losses), so you can improve and optimise your marketing strategy going forward.
Strengths of Marketing Mix Modelling
I’m sure you already have methods of finding insights in your marketing data.
However, it’s never easy.
Let’s take a look at the areas where Marketing Mix Modelling excels.
1. Get a Complete Analysis of Your Marketing Results
You’ll be able to see the results that every marketing channel delivered.
Not only that, but you’ll be able to see the impact that non-marketing related factors had.
For example, seasonal changes, or changes in general user behaviour.
Marketing mix modelling quantifies everything. So, you’ll have real numbers to back up your reports.
It’s important to note that you won’t have data on different campaigns within channels (we’ll talk about the limitations of MMM below).
2. High Statistical Reliability
Another benefit of MMM is that it’s statistically reliable.
After all, it’s based on an extensive data set, and you’re applying proven statistical modelling methods such as regression analysis.
Limitations of Marketing Mix Modelling
Unfortunately, there are limitations to Marketing Mix Modelling.
So, it might not be ideal for your marketing strategy. Let’s see why.
1. Designed With Traditional Marketing Channels in Mind
Marketing Mix Modelling was traditionally used to look at the impact of marketing tactics like:
- TV ads
- Magazine coupons
- Newspaper ads
These types of media don’t incorporate advanced targeting and messaging variants like we can do with online channels.
Marketing Mix Modelling doesn’t account for variations in messaging and creative used to target different audiences.
It only provides a top-down view.
A top-down view is nice-to-have, but it won’t show you an accurate picture of your individual campaign performance.
Because MMM shows averages over time, it ignores peaks and troughs.
For example, if your company was featured in TechCrunch and saw a huge traffic spike (that slowed down after a few days), your results would show an average for the whole period, and not account for the impact that a single media mention had at the time.
It can make specific channels look like they perform better on average than they usually do, because of rare events.
2. Too Complicated for Small Teams
Unfortunately, not all teams will have the bandwidth to use marketing mix modelling.
It requires knowledge of statistics to be done well.
If your company is small or doesn’t have anyone with knowledge about statistical analytics, then it’s probably not worth trying in-house.
You could work with a qualified external company, agency, or freelancer, and they’ll walk you through the process.
Although, that will cost you a lot of time and money.
3. No Guidance on Making Changes
Another downside to MMM over other marketing analysis methods is that you will get statistical data, but won’t receive any feedback on how you should make changes.
Considering marketers have access to tools that help us attribute our efforts to revenue, it’s worth considering if your time is well spent on MMM.
In many cases, using the tools you already have to gain insight into what’s working would be a more effective use of time.
How to Measure Marketing ROI with The Closed-Loop Framework
Even though I’ve provided more limitations of Marketing Mix Modelling than strengths, don’t dismiss it entirely if you regularly run offline marketing campaigns.
Marketing Mix Modelling remains a viable method for assessing offline marketing campaigns.
However, as I mentioned, there are other methods out there that will help you easily tie your digital marketing activities back to revenue.
And, you don’t need knowledge of statistical analytics to get access to this data!
If you want to see the link between marketing and revenue, you could consider using the Closed-Loop Framework.
It lets you see how all of your channels, both online and offline, are performing, and how well they can be attributed to conversions and sales.
Where the Closed-Loop Framework comes into its own is that with the right tools in place, you can completely automate the process.
Unlike the time-consuming MMM process, your data can be displayed in real-time and will account for all of your channels, campaigns, messaging, and any other marketing tactic you’re using.
For the Closed-Loop Framework to work, you will need a form of tracking to measure your visitors on an individual level, plus a CRM or robust web application to store your leads. Don’t have either of those? No need to worry! We will reference any tools used in our demonstration so that you can investigate them in more detail later on.
Let’s take a look at how the closed-loop framework works.
1. Track anonymous visitors over multiple sessions and traffic sources
Firstly, you need to track your anonymous visitors over multiple sessions and traffic sources for this to work.
We’re going to use our product to take you through the process.
Ruler Analytics visitor report
2. Send conversion data to the CRM
Whenever a visitor converts into a lead, the visitor level analytics matches up their marketing touchpoints to their conversion details.
If you’re managing a campaign that targets an offline audience, then you can still achieve this by using call tracking.
For this demonstration, however, we’re going to stick with forms.
Ruler Analytics forms report
Once the visitor analytics has matched up the lead with their marketing touchpoints, you’ll then need to pass this information onto your CRM.
Or, to wherever you store your leads i.e Google Sheets.
You’ll then be able to connect your marketing and conversion data directly to real customers.
Below is an example of what the conversion and marketing data looks like in Pipedrive.
3. Send sales revenue back to Analytics
Once these leads close into business, your sales revenue data is then sent back to Analytics, where it gets attributed to the channel it originated from.
Therefore closing the loop between marketing and sales.
Ruler Analytics forms report
After a quick setup, you’ll have access to all of the information you need to attribute your efforts to revenue and can go into your next marketing meeting with confidence.
There’s so much opportunity that you can get out of this framework.
But let’s say, at the end of the month, you populate a Closed-Loop report showing how much revenue you generated and which marketing touchpoints prospects interacted with the most before converting.
You may see that 90% of your revenue comes from customers who discovered you through a Google Paid campaign.
On the other hand, while you get a lot more traffic from Facebook Paid than Google Paid, only 10% of your revenue comes from your social media marketing initiatives.
With the Closed-Loop Framework, you will see that your social media campaigns are under performing in terms of revenue growth.
You decide to double down on Google Paid and slow down your social paid advertising, and the next month, you see a positive movement in sales.
We actually have a handbook which explains the Closed-Loop Framework and how to attribute sales revenue back to your marketing campaigns, channels and keywords.
You can download that here.
Marketing Mix Modelling is a statistically reliable way to track marketing effectiveness, but it falters when you’re running online campaigns across multiple channels, with numerous variants of messaging and creatives.
MMM isn’t designed to handle that level of detail.
It has several limitations that limit its effectiveness for marketing teams.
If you’re looking for a marketing reporting system that unifies data across online and offline channels and links your conversions directly to revenue, then the Closed-Loop Framework is for you.
The Closed-Loop Framework allows you to access revenue data and link it directly to your marketing activities without any of the headaches involved in Marketing Mix Modelling.