Metric Definitions That Hold Up
Define metrics precisely so every dashboard and team means the same thing
A taste of a lesson
We define an active user as 'logged in this month'. Product and marketing dashboards still disagree. Why?
That definition leaves several choices open, and each dashboard has probably made them differently. Which time zone defines the month? Are test and staff accounts excluded? Does someone using the app and the website count once or twice? Does an automatic login from a remembered session count as activity? Write one specification that answers each question, store it in a shared place, and point both dashboards to the same query. Start now: which of those four questions would change the number most for your product?
Written by the teacher as an example. In your lesson the tutor answers your own questions, and like any AI it can be wrong.
What you will be able to do
- Write a complete metric specification with exact rules
- Test definitions against edge cases before publishing
- Pair target metrics with guardrails to resist gaming
- Build a simple metric tree from goals to drivers
- Set up documentation and change logs so dashboards agree
Lesson plan
- 1 Anatomy of a metric Write a complete definition for one metric. Start
- 2 Edge cases Stress test a definition with awkward situations. Start
- 3 Ratios, averages and retention Avoid common traps with derived metrics. Start
- 4 Gaming and guardrails Design metrics that stay meaningful when targeted. Start
- 5 Metric trees Decompose a goal into driver metrics. Start
- 6 Documentation and governance Keep definitions consistent across teams and time. Start
Try asking
About this tutor
A tutor for analysts, product managers, founders and anyone who owns numbers, at any level. You will write metric definitions with an exact numerator, denominator, time window and inclusion rules, design metrics that resist gaming, organise them into a simple tree from goals to drivers, and document them so two dashboards never disagree silently. Lessons use common metrics such as active users, retention, conversion and revenue per customer, showing how small definition choices change the story. You finish with a metric specification template and a review routine for your organisation.
Reviews
4.3
3 ratingsSample
- Gustavo L.Sample
We found four different definitions of active user across our dashboards. The specification template fixed months of arguments.
- Hanna B.Sample
As a founder, the metric tree lesson helped me explain revenue changes to investors with less hand waving.
- Chidi N.Sample
The edge case drills were tedious in a good way. Our retention metric is much clearer now.
About the teacher
Data cleaning, SQL, exploratory analysis and honest charts
9 tutors 427 lessons taught Sample
I teach the part of data science that takes most of the time: getting data into a shape you can trust, querying it, exploring it and showing it honestly. I came to data from operations work, where reports drove real decisions and a wrong join could cost a week. I teach by handing you small, deliberately messy tables and asking...
See Lin's profile and tutorsMore like this
Other tutors on the same or nearby topics.