Hi all,
One of my clients is looking for best practices/ tips & tricks to working with control groups in AJO/AEP and wonder if you have anything in place?
His idea is to set it at profile level from AEP as a calculated attribute so they can use that information across touchpoints in the user journey. So a control group when sending out communication to recipients. Thanks in advance,Matteo
Solved! Go to Solution.
Views
Replies
Total Likes
Hi @Hemang35 ,
This is an answer i got from a consultant, thought to let you know also.
"Control groups is currently unsupported in AJO, but logged as enhancement request here: https://jira.corp.adobe.com/browse/CJM-11198. Also there is a seed list capability being discussed in here: https://jira.corp.adobe.com/browse/CJM-40621"
When working with control groups in Adobe Journey Optimizer (AJO) or Adobe Experience Platform (AEP), there are several best practices and tips that can help you get the most out of your testing and optimization efforts.
Here are some tips and best practices to consider:
Set control groups at the profile level: To ensure that your control groups are consistent across touchpoints in the user journey, it's a good idea to set them at the profile level as a calculated attribute. This will allow you to easily use the control group information when sending out communication to recipients.
Define your control group size: Your control group size will depend on several factors, such as the size of your overall audience, the complexity of your campaign, and the statistical significance you're trying to achieve. As a general rule, a control group size of at least 5% is recommended.
Randomize your control group: It's important to randomize your control group to ensure that it is representative of your overall audience. This can be done using AEP or AJO segmentation capabilities.
Monitor your control group performance: Keep a close eye on the performance of your control group throughout your campaign. This will allow you to adjust your strategy as needed and ensure that your test results are reliable.
Use your control group to measure lift: By comparing the performance of your control group to your test group, you can measure the lift generated by your campaign or experience. This will allow you to determine the impact of your optimization efforts and make informed decisions about future campaigns.
Overall, working with control groups in AEP or AJO requires careful planning, execution, and monitoring. By following these best practices and tips, you can ensure that your testing and optimization efforts are effective and reliable.
Excellent thanks for this insighful answer!
Views
Replies
Total Likes
Hi @Hemang35 ,
This is an answer i got from a consultant, thought to let you know also.
"Control groups is currently unsupported in AJO, but logged as enhancement request here: https://jira.corp.adobe.com/browse/CJM-11198. Also there is a seed list capability being discussed in here: https://jira.corp.adobe.com/browse/CJM-40621"
@Hemang35 Thanks for your approach. I'd really appreciate your detailed approach for Step 1. When you say setting them at the profile level as calculated attribute, what do you refer to more specifically? How could we set a control group as a calculated attribute, do you have any concrete example maybe which would really help me to understand your approach.
Views
Replies
Total Likes