Hey,

You probably get asked many times what campaigns are making a difference to your bottom line.

To really understand what is working and what isn’t all you need to do is add control groups to your campaigns. Control groups are the only way to measure the true incremental value each campaign has, compared to the baseline behavior of your customers. Therefore, it is the only way you can know exactly how much revenue to attribute to a specific campaign. With this information you can then decide whether a campaign is worth keeping or stopping.

As you know, Optimove make it as easy as possible for you to use control groups. We ensure customers are assigned in a representative way so that results have more statistical power and optimize their size to ensure you always maximize the number of customers receiving your campaigns.

This magazine issue is dedicated to knowing what is working. If you have any questions or comments, I’m only a reply away.

Cheers,

Shai Frank, VP of Product

Know you are making a difference

Control groups can help you know that you matter.

You know for a fact that some customers will make a purchase or deposit no matter what you do. Your goal is to create campaigns and journeys that move customers who are on the fence about making that transaction or increase the value of a transaction that would have been made either way.

Since control groups represent the baseline behavior of your customers, if your campaigns generate a statistically credible increase (aka “uplift”) on top of the control group, it means that you are making a difference.

There are many more benefits you can gain from using control groups. For our top choices check out this FAQ.

Know how to attribute results across campaigns

We’ve already established that control groups allow you to measure the incremental revenue (or any KPI) generated as the result of sending the specific campaign to a customer when compared to a similar customer who was not targeted with that campaign.

As such, incrementality is the unique marginal contribution of each specific campaign, making it the only solution to scientifically measure campaign attribution. For a detailed example of how this works across multiple campaigns click here.

Know you are optimizing the control group size

Even the most avid control group fans (that’s us) know that you always want to minimize control groups when campaigns are working well. That’s why we can automatically optimize the control group size for your recurring campaigns.

As test groups outperform control groups, Optimove gradually reduces the campaign’s control group size, allowing more customers to receive the campaign. The control group will never reach zero since you always want to be able to measure the campaign’s uplift as well as keep an eye out for changes in these results.

We recently looked at one year's worth of data and found that on average, it takes only three campaign occurrences to begin to see a reduction in control group size.

Know you are maximizing your opportunities

For some campaigns, a simple control group might not be enough. You might want to test more than one action, creating an A/B/n test with a control group. Self-Optimizing Campaigns will help you here while giving you the added benefit of matching actions to customer clusters ensuring maximal relevancy.

In other cases, you might want to test a series of campaigns, for example, your welcome series. Streams allow you to test a series of campaigns against a “super control group” to know if the entire series impacts customer behavior.

> From our blog

Blog: Combining Fast and Slow Data

True marketing magic happens when you combine “fast” and “slow” data. Learn more about combining these two data speeds in our latest blog post. Read more.