Why Do You Need A Media Mix Model?
Companies are swimming in a sea of marketing ROI analytics: Google Analytics, Facebook Analytics, Just-Trust-Me Analytics, etc. Seemingly they tell you all you need to know about how your marketing performs. But do they?
Simple case. A prospect sees a display ad that you placed through Liftoff. Then they do a search on Google and Bing. They see your ad on Facebook. Now they come to your website to do some research. Then your partner Criteo follows them around with more display ads. Finally, the prospect caves and buys when she accidentally sees your product at a discount offered by a third party reseller of yours. Why did she buy? How do you allocate this particular sale across all the touch points?
With the abundant ROI metrics provided to you by everybody this must be a piece of cake, right? Google will say it was because of them. Facebook will inform you the sale happened because of them. Bing, Criteo, Liftoff and a bunch of others will line up to take some (or rather ALL) credit for the sale. The third party reseller will take their share anyway and inform you that it was really the discount they offered that made this sale possible. The result is that with all the ROI tools and analytics you still have no idea what really happened. So what do you do?
Attribution modeling, they say. A little vague but most of the time this means that you need to roll up the analytics provided to you by everybody into one bottom-up attribution “model”. However, putting together several conflicting and mutually exclusive claims in the same spreadsheet or dashboard does not make them less conflicting and mutually exclusive. Now you have one place to get you confused instead of many.
I suggest a two step approach to get a real answer. First, build a top-down media/marketing mix model (MMM). Second, take the recommendations from the model and use rigorous experimental design tests to validate them.
Many marketers distrust MMM because it looks to them like a black box and for a non-statistician it actually is a black box. Are you going to feel better if I tell you that inside the box live strange creatures like GARCH, VAR, ARIMA and SARIMA? No? How about Durbin-Watson (no, not that Watson) and Augmented Dickey-Fuller? But wait, there is more…
The reality is that MMM is a very complex black box. Just like a computer is. Or like a BRM H16 sixteen-cylinder car engine that can deliver close to 600 hp. Do you understand even remotely how your phone works? Not really but you still use it anyway. I have to ask you to take the same approach to MMM. If it works, use it. And the only way to know if it works is to test the recommendations from the model.
So, what is a media mix model? click here
What skills are needed to build MMM? click here
Senior executive and expert in strategy and marketing | Podcast host | FinTech | HealthcareTech | EdTech
6 年I wish more companies understood the need for MMM. Unfortunately, most claim to be data driven but fall for the last-mile attribution trap all the time. I’ve had numerous futile conversations trying to explain that just because the final visit that resulted in the conversion came from paid search does not mean paid search is the best performing channel. This is a huge problem especially in the small business world where executives are averse to spending on sophisticated consultants and prefer to listen to the digital SEO/SEM “guru” who charges relatively small $ and offers “smoke and mirrors” analytics in Excel files.