Marketing mix modeling vs attribution: how they differ
Marketing mix modeling and digital attribution measure different things. The first works with aggregated data. The second follows each user's journey. This comparison helps to decide which question each one answers.
The comparison
| Aspect | Marketing mix modeling | Digital attribution |
|---|---|---|
| What data it uses | Aggregated data, such as sales per week and market | Each user's journey to the purchase |
| What media it covers | Digital and traditional media, and promotions | The digital media it can follow |
| External factors | It includes them, such as the season or the weather | It does not observe them |
| Personal data | The method does not need it | It depends on individual tracking |
| What it is most useful for | Reviewing investment as a whole | Adjusting digital campaigns |
When each one is most useful
Marketing mix modeling is most useful for reviewing investment as a whole. It compares digital media, traditional media and promotions on the same basis.
Attribution is useful for adjusting digital campaigns. It does not observe offline media.
The two methods can complement each other.
What their limits are
Neither of them proves on its own that an action caused a sale. Marketing mix modeling estimates contributions and depends on the quality of the data and the variables it includes. Attribution only sees what it can follow.
How to read your model with Xentinels
Xponentials builds your company's model. Xentinels lets you consult its results by market and period. The guide to marketing mix modeling explains the method in more detail.