Divvit offers various attribution models including our own machine learning multi-channel marketing attribution model.

Let's go over the differences of these different marketing attribution models: 

  • Machine learning multi-channel marketing attribution model: attribution is given to each channel considering the visit's position in the buying process, time on site, page-views and checkout visits. 
  • Classic last-click attribution: the last channel before purchase gets credit for the sale
  • Linear attribution (called weighted attribution): attribution is given to each channel involved in the purchase equally

There are clear differences in how machine learning multi-channel marketing attribution, linear attribution and last click attribution affect your revenue. Let's take this purchase as an example:

If we count this order in last click, the attribution looks like this:

While many analytics tools use last click attribution, we can see that this doesn’t show the full picture of the customer journey as we don’t count any channel other than the last channel. 

However, many marketers default to this model because it’s the easiest to use. 

If we use a linear attribution model, it looks more like this:

While linear attribution has its flaws as well, it’s important to count each and every touchpoint along the customer journey for a better understanding of how your channels impact your sales. 

Now, if we look at this purchase while using our machine learning multi-channel marketing attribution model, the purchase looks like this: 

Our machine learning multi-channel marketing attribution model will help you with: 

  • Know your exact CAC
  • Understand every customer journey
  • Learn which channels provide the best ROI
  • Discover which channels are over/undervalued

Discover more about attribution models and how to use them to maximize your ROI:

We would love to help you. Email us at support@divvit.com and we will help you with Attribution.

Did this answer your question?