how can we measure revenue per exposure with the new experiments functionality? I am trying to do average per user of sum(cash), but it seems it only counts users who purchased, instead of everyone who did experiment started
Hi Elena M., Please stand by as I search the Mixpanel knowledge base for an AI-powered answer. I normally take about 15 seconds or so. In case AI cannot answer your question, feel free to reach out to Mixpanel support at mixpanel.com/get-support. If you have follow-up questions for this thread, please tag me again with your question: @kapa.ai <follow-up question> 👋
Feel free to ask a follow-up question once I've answered by mentioning me with @kapa.ai
To measure "revenue per exposure" in Mixpanel Experiments, you want to calculate the average revenue (e.g., sum of a property like cash) per user who was exposed to the experiment, not just those who made a purchase.
How Mixpanel Calculates Group Rate for Value Metrics:
For value metrics (like revenue), Mixpanel's Experiments report calculates the group rate as:
Group Rate = Sum of property values ÷ Number of users exposed
This means the average is normalized over all users who were exposed to the experiment (i.e., those who triggered the $experiment_started event), not just those who made a purchase. For example, if your treatment group spent a total of $5,000 from 100 exposed users, the group rate would be $50 average per exposed user. This approach ensures you see the impact on your entire exposed user base, not just converters. This is important because a feature that increases average order value among buyers but reduces conversion rate might actually decrease overall revenue per user How do you read lift?.
If You’re Seeing Only Purchasers Counted:
If your current setup only counts users who purchased, double-check that your metric is set up as a value metric (e.g., sum of cash) and that it is being divided by the number of users exposed (not just purchasers). In the Experiments report, when you select a value metric, Mixpanel should automatically normalize by the number of exposed users, not just converters How do you read lift?.
Key Points:
- Use the Experiments report and select your revenue metric (e.g., sum of cash). - Mixpanel will calculate the average per exposed user (not just purchasers) by default. - If you are not seeing this, ensure your metric is set up as a value metric and not as a funnel or conversion metric.
If you are still seeing only purchasers counted, there may be a misconfiguration in your metric setup. In that case, try re-creating the metric in the Experiments report, ensuring you select the sum of the revenue property and let Mixpanel handle the normalization over all exposed users.
References: - How do you read lift? - Experiments Reference: Supported Metrics & Calculation Details
If you need to further diagnose or customize the analysis, you can click "Analyze" on a metric in the Experiments report to open a standard Insights report with the experiment breakdown applied, allowing you to verify how users are being counted Diagnosing experiments further in regular Mixpanel reports.
kapa.ai is still learning and improving, please let me know how I did by reacting below.
ℹ️ Tip: Mention @kapa.ai in the thread for follow-ups or DM the app for 1-to-1 help.
