Creating a Mixpanel Report to Compare Daily Homepage Views with Weekly Averages

Avi S. · 2025-01-29 01:31:56.070701+00

I am interested in creating a report which compares a data element from the previous day (ie. Homepage Views) to an average of the 4 previous weeks of that same day. For example, if yesterday was Monday, I would want to see a report which showed Monday’s Homepage traffic as compared to an average of last Monday, plus two weeks ago Monday, plus 3 weeks ago Monday plus four weeks ago Monday, averaged out. Can that calculation be done in Mixpanel? If so, how? Please advise.

Mixpanel is headed to Money20/20 October 26 - 29 in Las Vegas, Nevada!

Creating a Mixpanel Report to Compare Daily Homepage Views with Weekly Averages | Mixpanel Community

2 comments

· Sorted by Oldest

kapa.ai
APP
·
·
Hi Avi S., 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
kapa.ai
APP
·
·
Yes, this type of comparison can be done in Mixpanel using the Insights report and some advanced features. Here's how you can approach this: 1. First, create an Insights report for your "Homepage Views" event.2. Use the "Compare to past" feature to compare the current day to the previous 4 weeks. You can access this by clicking on the "Compare" menu at the top of your Insights graph.3. For the custom date range, you'll need to use a rolling time window. According to the Date Range documentation, you can use the "Last" option under Custom date range to set up a rolling time range.4. To get the average of the 4 previous weeks for the same day, you'll need to use a formula. Mixpanel supports creating formulas as mentioned in the Formulas documentation.5. In your formula, you'll need to add up the values for the 4 previous weeks and divide by 4 to get the average.However, there are some limitations to keep in mind: 1. Mixpanel's built-in time comparison features might not directly support this exact calculation out of the box.2. You might need to use JQL (JavaScript Query Language) to create a more complex custom query that can handle this specific time comparison. The JQL documentation shows how to use time buckets, which could be helpful in this case.3. The exact implementation might require some experimentation and possibly assistance from Mixpanel's support team, as this is a fairly complex query that goes beyond the standard features described in the provided knowledge sources.If you find that the built-in features of Insights don't provide enough flexibility for this specific calculation, you might want to consider exporting the raw data and performing the calculation in a separate analytics tool or spreadsheet.For the most accurate and up-to-date information on implementing this type of complex time comparison, I recommend reaching out to Mixpanel's support team directly. They can provide guidance tailored to your specific use case and the latest features available in the platform.
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.

kapa.ai
APP
·
·
Hi Avi S., 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
kapa.ai
APP
·
·
Yes, this type of comparison can be done in Mixpanel using the Insights report and some advanced features. Here's how you can approach this: 1. First, create an Insights report for your "Homepage Views" event.2. Use the "Compare to past" feature to compare the current day to the previous 4 weeks. You can access this by clicking on the "Compare" menu at the top of your Insights graph.3. For the custom date range, you'll need to use a rolling time window. According to the Date Range documentation, you can use the "Last" option under Custom date range to set up a rolling time range.4. To get the average of the 4 previous weeks for the same day, you'll need to use a formula. Mixpanel supports creating formulas as mentioned in the Formulas documentation.5. In your formula, you'll need to add up the values for the 4 previous weeks and divide by 4 to get the average.However, there are some limitations to keep in mind: 1. Mixpanel's built-in time comparison features might not directly support this exact calculation out of the box.2. You might need to use JQL (JavaScript Query Language) to create a more complex custom query that can handle this specific time comparison. The JQL documentation shows how to use time buckets, which could be helpful in this case.3. The exact implementation might require some experimentation and possibly assistance from Mixpanel's support team, as this is a fairly complex query that goes beyond the standard features described in the provided knowledge sources.If you find that the built-in features of Insights don't provide enough flexibility for this specific calculation, you might want to consider exporting the raw data and performing the calculation in a separate analytics tool or spreadsheet.For the most accurate and up-to-date information on implementing this type of complex time comparison, I recommend reaching out to Mixpanel's support team directly. They can provide guidance tailored to your specific use case and the latest features available in the platform.
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.