Credit rating changes

Confused by the 2005 value — is that a definition change?

Yes, exactly this.

The team discussed this at the standup. See /u/plg_arjun_pham/p/plot-0021.

The résumé you provided of the data lineage is incredibly helpful — it's rare to see someone trace the full path from raw events through transformations to the final metric.

Source?

The error is subtle but significant — we're including the zero-value placeholder rows in the sum, which inflates the total by roughly 12% compared to when we filter them out explicitly in the query.

The line thickness varies oddly. See /u/plg_arjun_pham/p/plot-0021.

Sounds right.

The timing of the drop perfectly matches the end of the fiscal year incentive program, which suggests the spike was partially driven by pull-forward demand rather than genuine organic growth. See /u/plg_arjun_pham/p/plot-0021.

The pattern appeared after the migration.

Milica al'Thor Are outliers winsorized or removed? See /u/plg_arjun_pham/p/plot-0021.

This is solid.

What's driving the spike in March?

Is this the same chart as /u/plg_arjun_pham/p/plot-0021? It seems different.

Same conclusion here.

Does the chart include partial weeks?

do you know whether 2017 was restated?

What happened to APAC around 2000?

Túpac Marchetti Very good.

Works for me.

This is much clearer, thanks.

I'm wondering whether the spike is driven by genuine demand or if it's an artifact of how we're aggregating across regional time zones — have we accounted for that temporal shift?

The 2022 break is a reporting lag — it shows up in every series from that source.

Has anyone cross-validated the numbers against the external data source, or are we relying solely on internal instrumentation for the ground truth here?

This aligns with what I expected. (edited to fix a unit)

Fair point.

Worth noting MEA and South Africa are not measured the same way over the post-2020 window. (edited to fix a unit)

Arjun Phạm This is accurate. See /u/plg_arjun_pham/p/plot-0021.

+1, and the US looks the same way.

Good catch.

Thanks , that resolves it.

Missing the latest append.

Amina Dalisar Have we investigated whether this is a real effect or just statistical noise within the 95% confidence band we'd expect given the sample size?

Which source is adjusted coming from?

Is this raw or adjusted? See /u/plg_arjun_pham/p/plot-0021.

Roger that.

this contradicts the other chart — one of the two is clipped.

I was thinking the same.

This was anticipated in the planning doc.

That's fair.

Absolutely.

Is the other chart built from the same extract?

Missing 2000.

Not sure what Year is measuring.

Consistent with prior year Q3.

Worth revisiting this after the next cycle.

Is the other chart built from the same extract?

Context for anyone new: unemployment is only comparable in absolute terms.

Should we consider the adjusted baseline instead?

I'm on board.

The calculation assumes that the cohort entry point is the user creation date, but our migration on the 8th re-stamped that field for ~8% of the base — we need a bridge analysis for that population. See /u/plg_arjun_pham/p/plot-0021.

Duplicated.

The pattern makes sense.

Yes, exactly this.

That's a solid approach.

Which source is baseline coming from?

Sorilea Beridze Fully aligned.

+1, and the US looks the same way.

Makes sense, thanks.

Nice work on the breakdown.

Can you split H2 out?

Milica al'Thor What's driving the spike in March?

Very good.

Wait, which of these is Brazil?

We saw similar behavior in 2023.

Thanks , that resolves it.

Which vintage?

The annotation arrows point to the correct values, but they're positioned so they obscure the peak — moving them outside the plot area or using a table for specific outliers would improve clarity.

Excellent presentation.

Worth noting Brazil and DACH are not measured the same way over the early years.

I'd agree with this direction.

Decimals are inconsistent between Brazil and India. (edited to fix a unit)

What is the refresh cadence on this? (edited to fix a unit)

Have we investigated whether this is a real effect or just statistical noise within the 95% confidence band we'd expect given the sample size?

Is this as a share of total, or raw?

this contradicts the other chart — one of the two is inverted. (edited to fix a unit)

Nicely done.

Confirmed on my side too.

Fixed.

Same conclusion here.

The units are missing from the tick labels.

Confirmed. See /u/plg_arjun_pham/p/plot-0021.

Amina Dalisar I'm convinced.

Is this in constant terms, or raw?

Why the drop-off after week 8?

Need to sync on next steps here.

The análisis looks solid.

That holds up.

Are outliers winsorized or removed?

Túpac Marchetti Worth noting — we should discuss methodology going forward.

Duplicated.

Definitely. See /u/plg_arjun_pham/p/plot-0021.

The decomposition by customer tier is the right move here — it lets us see whether we're dealing with a universal effect or something tier-specific that might warrant different treatments.

Danke for your diligent work on this — it's the kind of thoroughness that prevents embarrassing discrepancies from slipping into published reports that executives rely on.

This is solid.

Nasrin Andersen This is accurate.

Thanks for pulling this together.

For background: APAC changed reporting in 2006, which is why Q3 looks odd.

the secondary axis starts at zero for one series and not the other.

Amina Dalisar Sounds right.

Yep.

this contradicts the other chart — one of the two is clipped.

Can we see Benelux on the same scale?

Correcting myself: unemployment is in absolute terms, so the comparison holds.

Works for me.

Nasrin Andersen Spot on.

Thanks for catching that détail.

What's the retention rate?

Context for anyone new: GDP is only comparable as a share of total.

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. See /u/plg_arjun_pham/p/plot-0021.