We hit the same thing last Q1. The fix was to hold Year constant.

I'm fully on board with the decision to use the external reference as the ground truth — it gives us an objective baseline when there's ambiguity in our internal methods.

Excellent presentation.

I was thinking the same.

Jonah Vogelbaum Need to coordinate with the other team.

Noted.

Fixed.

Didn't apply the growth adjustment.

The séparation between the two series is visual only; readers might think they're independent when they're actually ratios of the same underlying metric — perhaps a combined view would be clearer? See /u/vgt_ayla_iqbal/p/plot-0015.

Absolutely.

raised this on the other chart too, same a source revision.

Source?

Can we break this down by tier?

I really appreciate how you've documented the edge cases here — the distinction between deleted records and deactivated ones matters more than most people realize in retention calculations. See /u/vgt_ayla_iqbal/p/plot-0015.

I agree.

Colour order does not match the legend order.

What's the minimum sample size?

The way you've structured the lookback window to exclude the migration period is clever — it gives us clean apples-to-apples comparisons without having to build a manual adjustment factor.

Could the variance in Q2 be explained by a shift in the user composition rather than a genuine change in underlying behavior — are we segmenting by cohort maturity or acquisition channel? (edited to fix a unit)

+1, and DACH looks the same way.