Retrics

PLATFORM · PREDICTIONS

Every customer has a rhythm.

Retrics learns it from her own orders and flags the week she'll need to buy again.
LIVELIVE IN THE RETRICS APP · RE-SCORED ON EVERY SYNC
REORDER WINDOW

DAYS 31–45

FROM THE INTERVALS BETWEEN HER OWN ORDERS

LAPSE RISK

1.8× HER CADENCE

DRIFT PAST HER RHYTHM — NOT DAYS PAST A STORE-WIDE MEAN

RETURN PROBABILITY

64%

MARKER SITS AT THE ~2.7% NATURAL-RETURN FLOOR

CONFIDENCE

VERY LIKELY

VERY LIKELY · LIKELY · UNCERTAIN · UNLIKELY — BANDS, NOT DECIMALS

HEALTH BAND

THRIVING

THRIVING80–100
COOLING40–59
LOSTunder 20
WHY, IN WORDS

5 RANKED FACTORS

CADENCE · FREQUENCY · VALUE · BASKET TREND · REFUNDS

SECOND-ORDER WINDOW

3.2× IN THE WINDOW

12-MONTH BACKTEST OF REAL ORDERS — FLAG PRECISION, NOT CAUSAL LIFT

FORECAST

NEXT 30 & 90 DAYS

MODELLED REORDER REVENUE — AND LABELLED AS MODELLED

CONCEPT PREVIEW · NUMBERS ILLUSTRATIVE

01 — CADENCE

Her rhythm, not a segment average.

The window comes from the intervals between her own orders. Lapse risk is drift past that cadence.

every synceach customer re-scoredhealth, return-probability, and reorder window recomputed as orders land.
ONE CUSTOMER · HER OWN INTERVALSDAYS →

RETURN PROBABILITY

64%

READ AGAINST THE FLOOR

~2.7%

CONFIDENCE BAND

Very likely

A WINDOW, NOT AN APPOINTMENT — THE WEEK, NOT THE DAY

CONCEPT PREVIEW · NUMBERS ILLUSTRATIVE

02 — THE METHOD

Where a score comes from, and where it stops.

CONCEPT PREVIEW · NUMBERS ILLUSTRATIVE
HER OWN INTERVALS

MEDIAN, NOT MEAN

ONE HOLIDAY GAP CANNOT MOVE THE WINDOW

PER PRODUCT

CONSUMABLES DIFFER

A GRINDER AND A BAG OF BEANS ARE NOT ONE CLOCK

ONE-ORDER FALLBACK

STORE TYPICAL

UNTIL SHE HAS A RHYTHM OF HER OWN

OVERDUE COUNTDOWN

11 DAYS PAST

THE WINDOW CLOSED, AND THE PROFILE SAYS SO

THIN SAMPLE

NO RATE AT ALL

UNDER TEN BUYERS A REPEAT RATE IS NOT SHOWN SMALL — IT IS NOT SHOWN

COHORTS

MONTHLY TRIANGLE

SURVIVAL BY ACQUISITION MONTH

RFM GRID

5×5, REVENUE PER CELL

THE WHOLE BASE, NOT ONE CUSTOMER

RE-SCORED

ON EVERY SYNC

AS ORDERS LAND, NOT ON A MONTHLY BATCH

IT FEEDS BOARDS

REORDERS · WIN-BACK

A RANKED LIST, NOT AN OUTBOX

IT FEEDS THE BRIEF

TODAY'S TOP MOVES

ONE PRINT-CLEAN PAGE EACH MORNING

IT FEEDS AN AUDIENCE

FROZEN, WITH A CONTROL

YOU WRITE THE MESSAGE — RETRICS PICKS WHO, AND WHO IS HELD BACK

IT NEVER SENDS

RANK AND FLAG ONLY

NOTHING MOVES ON A MODEL'S SAY-SO

WATCH IT PREDICT

See the reorder
before it happens.

Retrics learns a customer’s rhythm from her own intervals once she has enough of them — the product’s or your shop’s median until she does — flags the week she’ll need to buy again, and reads it against the natural-return floor.

WINDOWS, NOT APPOINTMENTS · RE-SCORED ON EVERY SYNC

Drift radarSCANNING 14,208 CUSTOMERS
C-4821

8 orders · due in 6 days

HELD
C-1177

3 orders · 71 days quiet

WIN-BACK RANKED
C-9204

5 orders · 44 days quiet

WIN-BACK RANKED
C-3358

12 orders · steady

HELD
WOULD BE CLAIMED · WITHHELD TODAY$0

CONCEPT PREVIEW · NUMBERS ILLUSTRATIVE · YOU WRITE THE MESSAGE

03 — READ AGAINST THE FLOOR

Scored against the floor, not hope.

Every return probability is read against the ~2.7% of lapsed customers who come back with no outreach at all. If she'd return anyway, Retrics says so.

TWO CUSTOMERS · ONE FLOORRETURN PROBABILITY →
LAPSED · DRIFTED PAST HER CADENCEFLAGGEDLAPSED · BUT RETURNS ON HER OWNNOT FLAGGEDFLOOR ~2.7%

THE FLOOR IS WHAT COMES BACK WITH NO OUTREACH AT ALL · CLEARING IT BY A LITTLE IS NOT A WIN

CONCEPT PREVIEW · NUMBERS ILLUSTRATIVE

04 — WHAT IT FEEDS

Predictions rank. They never send.

Every score becomes a board, a brief, or an audience frozen with its control held back — waiting on the message you write and the approval you give it.

BEFORE YOU ASK

Straight answers.

Q01What about customers with only one order?

One order isn't a rhythm yet, so Retrics falls back to how that product is typically repurchased across your store — and watches the second-order window closely, because that is where the strongest measured effect lives. Once she orders again, her personal cadence takes over.

Q02How accurate are the predictions?

Honestly: they are windows, not appointments — the week a customer is likely to need to reorder, not the day. The method is validated on a 12-month backtest of real orders, which measures how precise the flag is rather than what a message causes. A controlled send is read against its own holdout's observed return rate; an audience too small to carry a control is read observationally against the fixed ~2.7% natural-return floor instead. The recovered-revenue figure is withheld today. The holdout is still carved and never messaged on every eligible send, so the evidence accumulates — but the comparison is being rebuilt to count only the customers a message actually reached, and Retrics won’t publish a dollar measured over anything looser. The full method — holdout design, the floor, the backtest windows — is set out in the method section on this page.

Q03Do predictions ever send anything on their own?

No. Predictions only rank and flag. A score can freeze an audience and carve the control that will measure it, but the message is yours to write and yours to approve — and nothing sends on your approval either, because what approval produces is a campaign-safe export you send from your own platform.

See your own customers' rhythms.

Connect your store and Retrics scores your real order history the same day.