proof
Measured, not promised.
Every figure here is scored against a holdout. The ~2.7% of lapsed customers who return with no outreach at all are subtracted before we claim a dollar.
the ledger rule
The number gets smaller. And truer.
3.2×
second-order window lift
The model was frozen at a cutoff date and graded only on the orders that really followed. First-time customers reached inside their predicted window placed a second order at 3.2× the rate of comparable customers outside it.
12-month backtest of real Shopify orders, holdout-scoredCustomer logos we haven’t earned.
ROI multiples we awarded ourselves.
Aggregates, while the honest sample is one.
Projections dressed as actuals.
One holdout-scored finding, provenance attached. That's the page.
Run it on your own twelve months.
The trial replays your own order history — your cadences, your second-order window — measured the same way, before you pay anything.
No credit card · read-only Shopify scopes · live in ~10 minutes