Top Nutrition Coaching · Whales & Minnows by Billing Type · v5 · April 2026

Two different businesses, two different whales.

Insurance and Self-Pay produce whale customers that look almost nothing alike. The Insurance whale is a 35–54 woman on Aetna; the Self-Pay whale is a 65+ man on weekly subscription. Every pattern below is tagged with how confident we are that it's real vs just a coincidence in the data.

How to read this dashboard

The vocabulary in 60 seconds.

What is mLTV?

mLTV = "marginal LTV" = revenue collected − clinical cost (dietitian pay) per client. It's the contribution margin per customer in dollars. A customer at $200 mLTV has generated $200 of profit after paying the RD. Higher mLTV = more valuable customer. This is what paid media should optimize against — not revenue, not bookings.

Whale vs Minnow

Whale = top 10% of clients by mLTV. They drive most of the margin. Minnow = clients with negative mLTV — we lose money serving them. The middle 70-80% sit between. Targeting strategy is to find more whales and avoid minnows.

Where signals come from

Two sources: quiz answers (what the customer told us before they paid — sleep, stress, energy, anxiety, goal, insurer, age, state, gender) and operational data (sessions attended, no-shows, billing cadence, claim reimbursement %). Quiz answers are the only signals we can use for paid-media targeting at acquisition. Quiz-sourced signals are tagged below with QUIZ.

Positive vs negative signal

Each signal in the tables below points one direction or the other:

↑ POS for mLTVTrait predicts higher mLTV. Bid up, target more.
↓ NEG for mLTVTrait predicts lower mLTV. Bid down, exclude.
01 · Before anything else

What this analysis is based on.

Four decisions that shape every number below

01

Who's in the data

1,869 clients who signed up between Sep 1, 2025 and Jan 20, 2026. Everyone has had at least 3 months of tenure by the reference date (Apr 22, 2026). Average tenure in the cohort: 4.8 months. Anyone newer is excluded — insurance claims take 30–90 days to process and margin mostly settles by month 5–6, so newer clients haven't had time to show their real behavior.

02

mLTV is margin, not revenue

For each client: net revenue − clinical cost, where clinical cost is $60/hour of dietitian labor on every occurred session, no-show, and late-cancel — dietitians are paid for all three. Standard cancels, reschedules, and pending appointments cost us nothing.

03

Dollars, not per-month rate

mLTV is the observed margin per client over their full tenure — we don't divide by months. A client with 6 months of tenure who produced $300 of margin has an mLTV of $300. These are not annualized or projected figures.

04

Confidence tested on every signal

We ran a Fisher's exact test on every whale/minnow pattern to check whether the pattern is real or just coincidence in the data. Each row in the signal tables shows a confidence %. 95%+ clears the standard bar for statistical significance.

Why we picked 3 months as the cutoff: margin accumulation per additional month of tenure drops sharply after month 3 for Insurance (from roughly +$46/month in month 2 to +$5/month by month 5). Most of a client's behavioral signal — whether they activate, how many sessions they do, how their claims reimburse — has surfaced by month 3. Going earlier adds noise without signal; going later would cut the sample size (only 387 clients have 6+ months of tenure).
02 · Headline

Average mLTV per client.

Overall mLTV
$120
Average mLTV across 1,869 clients. About half of clients actively produce margin; the other half sit at $0 or negative.
Revenue per client$182
Cost per client$62
Insurance · 89% of cohort
$112
1,659 clients · 47% activate
Revenue $174 · cost $62
Active clients average $251
12% lose money
Self-Pay · 11% of cohort
$187
210 clients · 60% activate
Revenue $252 · cost $65
Active clients average $321
18% lose money
03 · Insurance Performance

mLTV by insurance provider.

Customer-stated insurance provider performance breakdown for the Insurance cohort (1,659 clients):

Insurance Provider Sample Size mLTV vs Avg ($112)
Anthem 78 $165 +$53
Aetna 142 $158 +$46
Blue Cross Blue Shield 356 $125 +$13
United Healthcare 164 $98 −$14
Cigna 106 $94 −$18
03 · The shape

Self-Pay has a longer tail — both follow a power law.

Most clients produce very little. A small group at the top produces most of the margin. Here's how the margin spreads across clients, split by billing type (clients sorted by mLTV, then grouped into deciles of equal size):

Insurance mLTV by decile

1,659 clients · total mLTV $185,618 · average $112
Decile
Average mLTV (scaled)
Average mLTV
Top 10%
$584
2nd 10%
$280
3rd 10%
$178
4th 10%
$116
5th 10%
$41
30% ghosts
$0
9th 10%
−$11
Bottom 10%
−$67

Self-Pay mLTV by decile

210 clients · total mLTV $39,294 · average $187
Decile
Average mLTV (scaled)
Average mLTV
Top 10%
$884
2nd 10%
$487
3rd 10%
$285
4th 10%
$177
5th 10%
$74
6th 10%
$13
20% ghosts
$0
9th 10%
−$2
Bottom 10%
−$46
Insurance: four types of client

1,659 clients → $185.6k total mLTV

Whales
165
top 10% → 52% of mLTV
Middle
615
positive but not whales
Ghosts
674
41% — did nothing
Minnows
205
12% — lost money
Self-Pay: four types of client

210 clients → $39.3k total mLTV

Whales
21
top 10% → 47% of mLTV
Middle
94
positive but not whales
Ghosts
57
27% — did nothing
Minnows
38
18% — lost money

The Self-Pay whale is bigger: $884 vs Insurance's $584 (51% more margin per client). Self-Pay has fewer ghosts (27% vs 41%) because asking for a credit card upfront filters out people who wouldn't engage anyway. Self-Pay minnows cost less to lose money on ($46 vs $67) because they churn out of subscription before accumulating many no-show fees.

04 · How to read the next sections

What the confidence dots mean.

The next two sections have signal tables — things that are more common among whales or minnows than among everyone else. Each row has a dot showing how confident we can be that it's a real signal, not just a coincidence in the data. The % shown is the chance the pattern is real.

Confidence key
99%+ — Very strongBet the budget on it.
95–99% — SolidReal pattern. Act on it.
90–95% — SuggestiveProbably real. Test before committing big budget.
Below 90% — Not provenCould be noise. Don't act on this yet.

"Lift" is how much more (or less) common something is among the target group. 1.43× lift means whales are 43% more likely to have that trait than other clients. 0.60× lift means whales are 40% less likely to have it. Both directions are informative.

05 · Insurance · the whale profile

The midlife woman on Aetna, "feeling hopeful."

Insurance Whale · top 10%
The Hopeful Returner

A 35–54 woman on Aetna or BCBS. Says she's "feeling hopeful" at signup, reports moderate stress, doesn't flag anxiety, sleeps 5–6 hours. Wants to build muscle and lose fat. Books fast, shows up, does 5 sessions over her first 5 months.

Average mLTV
$584
5× the Insurance average
Sessions attended
5.4
vs Insurance average of 1.3
No-shows & late cancels
0.16
basically always shows up
Insurance reimburses
49%
of billed claims
Gender87% women · 13% men
Age35–54 is the core. Not 65+ — that's Self-Pay territory.
Top statesTexas 15% · Florida 9% · Illinois 8.5% · California 6% · Virginia 6%
Best insurerAetna — 19% of whales are on Aetna, vs 14% of other Insurance clients
MotivationPicks "feeling hopeful" at signup — 28% of whales vs 21% of others
PsychologyModerate stress, no anxiety/depression flag
Sleep5–6 hours per night — the single strongest pattern we have
GoalBody recomposition: build muscle and reduce body fat
Insurance Minnow · loses money
The Copay Ghost

Looks similar demographically to the whale, but 20% male. Books one appointment, pays one copay, then no-shows or late-cancels roughly once. Their insurance ends up reimbursing only 37% of billed claims. Slightly over-represented on Anthem plans.

Average mLTV
−$63
we lose ~$60 per client
Sessions attended
0.11
almost no one shows up
No-shows & late cancels
1.02
6× the whale rate
Insurance reimburses
37%
12 points below whale
Gender79% women · 20% men (slightly over-indexed vs whales)
AgeSkews 35–44. 55–64 almost never become minnows
Top statesFlorida 11% · Texas 11% · California 8% (geography barely matters here)
Insurer flagAnthem — 13% of minnows vs 9% of others · UHC and BCBS don't stand out
ChannelSlightly more Facebook paid — but we can't confirm this statistically yet
MotivationThe absence of "feeling hopeful" is a mild warning sign
BehaviorClaims reimburse at 37% vs 49% for whales — bad plan tiers or unmet deductibles

What makes an Insurance whale — ranked by confidence

Signals that predict a whale

Each row shows a trait and how common it is among whales vs everyone else
Traits whales have more often ↑ POS for mLTV
Sleeps 5–6 hours a night QUIZ 45% of whales say this vs 31% of others
43% more likely
99.9% confident
Energy "moderate but fluctuates" QUIZ 33% of whales vs 24% of others
35% more likely
98% confident
Acquired through Google paid search 84% of whales vs 75% of others
11% more likely
98% confident
Goal is body recomposition (build muscle + cut fat) QUIZ 31% of whales vs 23% of others
36% more likely
98% confident
Says "I'm feeling hopeful" at signup QUIZ 28% of whales vs 21% of others
35% more likely
96% confident
No anxiety or depression flag QUIZ 22% of whales vs 16% of others
41% more likely
96% confident
Self-reports moderate stress QUIZ 50% of whales vs 42% of others
21% more likely
96% confident
Covered by Aetna QUIZ 19% of whales vs 14% of others
43% more likely
95% confident
Lives in Illinois QUIZ 8.5% of whales vs 4.8% of others
76% more likely
94% confident
Traits whales have less often ↓ NEG for mLTV
Covered by Cigna QUIZ 6% of whales vs 10% of others — Cigna is underrepresented among whales
40% less likely
90% confident
Lives in Texas QUIZ 15% of whales vs 11% of others — directional but not proven
35% more likely
85% confident
Age 55–64 QUIZ 16% of whales vs 13% of others — tilt but not proven
28% more likely
78% confident
Never tried weight loss before QUIZ 3.6% of whales vs 2.3% of others — small numbers
55% more likely
71% confident

Signals that predict a minnow

Each row shows a trait and how common it is among minnows vs everyone else
Traits that flag a minnow (red flags) ↓ NEG for mLTV
Male gender QUIZ 20% of minnows vs 15% of others
36% more likely
94% confident
Covered by Anthem QUIZ 13% of minnows vs 9% of others
43% more likely
92% confident
Acquired through Facebook paid ads 2.9% of minnows vs 1.7% of others — suggestive but not enough data to prove
77% more likely
75% confident
Age 35–44 QUIZ 33% of minnows vs 29% of others — slight tilt, not proven
16% more likely
81% confident
Traits that protect against being a minnow (green flags) ↑ POS for mLTV
Age 55–64 QUIZ Only 9% of minnows are in this age range, vs 14% of others — late 50s / early 60s rarely become minnows
36% less likely
95% confident
Says "I'm feeling hopeful" at signup QUIZ 17% of minnows vs 22% of others — "feeling hopeful" clients rarely go negative
25% less likely
92% confident
Female gender QUIZ 79% of minnows vs 83% of others
6% less likely
91% confident
Acquired through Google paid search 71% of minnows vs 77% of others
7% less likely
90% confident
Insurance takeaway

Eight whale-predicting traits are statistically solid. Use these for bidding.

The strongest patterns we can confirm are: sleep 5–6 hours, moderate fluctuating energy, acquired via Google CPC, body-recomposition goal, "feeling hopeful" motivation, no anxiety/depression, moderate stress, and Aetna coverage. A client hitting 4+ of these at quiz time is meaningfully more likely to become a whale. Stack these as a scoring signal in Meta/Google audience modeling.

On the minnow side, the evidence is weaker. The best-confirmed pattern is a protective one: age 55-64 clients rarely become minnows. For red flags, male gender (94% confident) and Anthem coverage (92%) are suggestive but not confirmed. The Facebook paid ads signal is intuitive but we don't have enough Facebook-acquired clients in the data to prove it yet.

06 · Self-Pay · the whale profile

The retired man on weekly subscription.

Self-Pay Whale · top 10%
The Subscription Senior

65+, disproportionately male (38% — unusual for us), on weekly billing, lives in NY, TX or IL. Pays 16 times over ~5.5 months and actually shows up to 5–6 sessions. Says "I'm ready" at signup. Low-to-moderate stress.

Average mLTV
$884
4.7× the Self-Pay average
Revenue per client
$1,002
over tenure
Payments made
16
nearly 3× their session count
Sessions attended
5.7
over 5.5 months
Gender52% women · 38% men — the only whale profile where men are this well-represented
Age48% are 65+ · 19% are 55–64. Under 45 is rare (14% combined).
Top statesNew York 19% · Texas 10% · Nevada 10%. Zero California whales in this data.
Billing cadence86% are on weekly billing · 14% bi-weekly. Zero are on monthly.
MotivationSays "I'm ready" at signup — 57% of whales vs 32% of other Self-Pay clients
PsychologyLow-to-moderate stress, no anxiety/depression flag
ChannelMostly Google paid search · zero came through Facebook paid
Self-Pay Minnow · loses money
The Prepaid Dropout

45–54 year old, more likely male. Starts a subscription, does 0–1 sessions, cancels within a month or two. Mean revenue $18, mean cost $45. Smaller sample size means most patterns aren't statistically confirmed — but the 45–54 age pattern is strong.

Average mLTV
−$27
smaller loss than Insurance minnow
Revenue per client
$18
one or two payments
Payments made
1.8
vs whale's 16
Sessions attended
0.4
most never attend
Age45–54 is 3× more common here than elsewhere — the strongest confirmed pattern
GenderMore men than non-minnow Self-Pay (26% vs 15%)
Top statesCA, NY, PA, FL, MI — but no state effect reaches statistical significance
BillingSuggests monthly cadence churns faster, but we can't confirm — too few monthly subscribers
ChannelThe one Facebook-acquired Self-Pay client in the data is a minnow — indicative but way too small to prove anything
PsychologyTilts toward high stress and anxiety/depression flagged — but not confirmed
ProtectiveAge 55-64 almost never becomes a minnow (though not yet confirmed)

What makes a Self-Pay whale — ranked by confidence

Signals that predict a whale

Only 21 Self-Pay whales in the data — signals need to be strong to clear stat-sig
Traits whales have more often ↑ POS for mLTV
Age 65+ QUIZ 48% of whales are 65+, vs 11% of other Self-Pay clients
4.3× more likely
100% confident
On weekly billing (not monthly or bi-weekly) 86% of whales are on weekly billing, vs 40% of others
2.1× more likely
100% confident
Male gender QUIZ 38% of whales are men, vs 14% of other Self-Pay clients
2.7× more likely
99% confident
Lives in New York QUIZ 19% of whales are in NY, vs 4% of others
4.5× more likely
98% confident
Says "I'm ready" at signup QUIZ 57% of whales vs 32% of others · note: for Insurance the equivalent signal was "feeling hopeful"
80% more likely
97% confident
Age 55–64 QUIZ 19% of whales vs 6% of others
3.0× more likely
94% confident
Traits whales have less often ↓ NEG for mLTV
On monthly billing Zero whales are on monthly billing — it's a lite-commitment tier that doesn't produce whales
100% less likely
91% confident
Acquired through Google paid search 62% of whales vs 41% of others — just misses statistical significance
50% more likely
90% confident
Self-reports moderate stress QUIZ 43% of whales vs 26% of others — likely real but not yet confirmed
65% more likely
88% confident
Lives in Texas QUIZ 10% of whales vs 3% of others — small numbers
3.0× more likely
82% confident
Self-reports low stress QUIZ 24% of whales vs 13% of others
80% more likely
81% confident

Signals that predict a minnow

Only 38 Self-Pay minnows — most patterns need more data to confirm
Traits that flag a minnow (red flags) ↓ NEG for mLTV
Age 45–54 QUIZ 16% of minnows vs 5% of others — the one confirmed Self-Pay minnow signal
3.0× more likely
97% confident
Male gender QUIZ 26% of minnows vs 15% of others · note: men also over-index as whales — it's high-variance for Self-Pay
81% more likely
91% confident
Weekly billing 55% of minnows vs 42% of others — most Self-Pay clients are on weekly anyway
30% more likely
85% confident
Anxiety/depression flagged at signup QUIZ 24% of minnows vs 16% of others — suggestive but not confirmed
45% more likely
66% confident
Self-reports high stress QUIZ 24% of minnows vs 17% of others — suggestive but not confirmed
40% more likely
65% confident
On monthly billing 18% of minnows vs 13% of others — tilts toward minnow but can't confirm
44% more likely
57% confident
Traits that protect against being a minnow (green flags) ↑ POS for mLTV
Age 55–64 QUIZ 3% of minnows vs 9% of others · directional but small n
70% less likely
69% confident
Female gender QUIZ 34% of minnows are female vs 46% of others
26% less likely
79% confident
Self-Pay takeaway

Only 5 whale signals clear 95% confidence — but they're extremely strong and stack together.

The confirmed Self-Pay whale pattern is a tight cluster: age 65+, weekly billing, male, living in NY, saying "I'm ready". These aren't independent signals — they describe one concentrated profile. 48% of Self-Pay whales are 65+ and 86% are on weekly billing; those two overlap significantly.

The monthly-billing result is striking: zero whales in our data are on monthly billing. That's consistent with the theory that weekly debits create stronger commitment than monthly ones. We're 91% confident this is real — it's worth testing by making weekly the default tier.

Almost everything else on the Self-Pay side doesn't reach statistical significance because we only have 21 whales and 38 minnows in the data. As more Self-Pay clients age past the 3-month mark over the next quarter, more patterns will emerge.

07 · What to do about it

Four moves, confirmed signals only.

Insurance · targeting

Build a whale score from the 8 confirmed traits.

Score each lead by how many of these they show: sleep 5-6 hours, moderate fluctuating energy, Google paid search channel, body-recomposition goal, "feeling hopeful" motivation, no anxiety/depression flag, moderate stress, Aetna coverage. Clients hitting 4+ signals should be bid up in Meta/Google audience modeling. Don't over-extend on the directional-only patterns (Illinois, Texas, Cigna avoidance) — worth testing but not ready to commit big budget.

Self-Pay · targeting

Target 65+ men and women in NY, guide them to weekly billing.

The 5 confirmed signals stack tightly on one profile: retired audience, NY metro, weekly-subscription landing page, "I'm ready" framing. Run separate creative for this audience — completely different from the midlife Insurance whale. Kill monthly billing as a default tier (zero whales, and we're 91% confident that's not a coincidence).

Funnel · minnow friction

Add a booking commitment step to filter out ghosts without bothering whales.

Insurance minnows no-show or late-cancel roughly once each. Insurance whales do it 0.16 times. A small deposit, mandatory SMS confirmation 24 hours before, or a paid cancellation policy would filter most of the minnow volume without affecting whale behavior. Applies to both Insurance and Self-Pay — targeting 45-54 year olds in Self-Pay specifically for the extra friction is worth testing.

Validate before scaling

Run tests on the directional (90-94%) signals before committing budget.

Worth testing for 4-6 weeks and revalidating: Facebook paid as a minnow predictor (75% today), Anthem coverage as a minnow predictor (92%), Illinois as an Insurance whale signal (94%), Cigna avoidance (90%), and "feeling hopeful" as a protection from becoming a minnow (92%). Segment your campaigns by these and measure mLTV on the resulting cohorts.

08 · Value-based bidding

What mLTV value to pass back to ad platforms.

For value-based bidding to work, every conversion event needs to fire with a dollar value attached. Higher values tell Meta and Google to bid harder for similar users. The trick is figuring out what value to send. Below: a scoring recipe using only the signals we trust on two grounds — Fisher's exact confidence at 95%+, and at least 30 supporting whale observations behind the signal. Statistical significance alone isn't enough. A signal with 4 supporting whales can be 98% significant and still have a $271 estimate that's actually anywhere from $50 to $500. Anything that fails either filter goes to a watch list — track but don't bid on.

How the math works

Baseline + signal uplifts, capped at the whale ceiling. Only signals with enough whales behind them.

Every conversion fires with a baseline mLTV (the cohort average). Each confirmed positive signal observed at quiz time adds an uplift. Confirmed negative signals subtract. The total is capped at the top-decile (whale) value so a stack of correlated signals can't blow out to an unrealistic number.

passback = baseline + Σ uplifts Σ downlifts   capped at [ $0, whale_ceiling ]

Two filters apply before a signal earns a passback uplift. The first is statistical significance — a Fisher's exact test must clear 95% confidence that the difference isn't zero. The second, equally important, is sample size: at least 30 supporting whale observations behind the signal. Significance tells us the direction is real; sample size tells us the magnitude is stable. A signal with 4 whales behind it can be 98% statistically significant and still have a $271 uplift estimate that's actually anywhere from $50 to $500. Passing imprecise estimates to ad platforms wastes budget chasing phantom audiences.

Signals that clear significance but fail the n≥30 sample bar go to the watch list. Track them, monitor as the cohort grows, but don't pass them back yet.

Baselines and ceilings

Fire these as the default value for any conversion of each type, then layer uplifts on top.

Insurance conversion
Baseline valuecohort average — fire when no quiz signals captured
$112
Whale ceilingcap the final passback value here
$584
Floornever pass back negative values
$0
Self-Pay conversion
Baseline valuecohort average — fire when no quiz signals captured
$187
Whale ceilingcap the final passback value here
$884
Floornever pass back negative values
$0

Insurance signal uplifts

All quiz-captured. All clear both filters: 95%+ confidence on Fisher's exact test, and 30+ supporting whale observations.

Tier 1 — 99%+ confidence PASS BACK

Sleeps 5-6 hours a night QUIZ43% more likely to be a whale · 99.9% confident · supported by n=74 whales · single strongest Insurance signal
+43% lift
+$23

Tier 2 — 95-99% confidence PASS BACK

Covered by Aetna QUIZ43% more likely to be a whale · 95% confident · supported by n=31 whales
+43% lift
+$23
No anxiety or depression flag QUIZ41% more likely to be a whale · 96% confident · supported by n=36 whales
+41% lift
+$22
Goal is body recomposition QUIZ36% more likely to be a whale · 98% confident · supported by n=51 whales · "build muscle + reduce body fat"
+36% lift
+$19
Energy "moderate but fluctuates" QUIZ35% more likely to be a whale · 98% confident · supported by n=54 whales
+35% lift
+$18
Says "I'm feeling hopeful" at signup QUIZ35% more likely to be a whale · 96% confident · supported by n=46 whales
+35% lift
+$18
Self-reports moderate stress QUIZ21% more likely to be a whale · 96% confident · supported by n=82 whales
+21% lift
+$11

Watch list — fails sample size bar DO NOT PASS BACK

Age 55-64 (protective signal) QUIZ36% less likely to become a minnow · 95% confident · but only n=15 minnows in this segment — below the n≥30 bar. Re-evaluate at the next quarterly refresh.
−36% minnow
WATCH

If a customer fires every Insurance pass-back signal at once, the raw stack adds to $134 of uplift on top of the $112 baseline = $246 total. That's well below the $584 ceiling, so the cap rarely binds for Insurance conversions.

Self-Pay signal uplifts

Important — Self-Pay sample is too small for per-signal passback today

All Self-Pay signals fail the n≥30 sample bar. Pass back the $187 baseline only.

The Self-Pay cohort has 21 whales total. Even the strongest signal — Age 65+ — is supported by only ~10 whale observations. The lift estimates are statistically significant (Fisher's exact clears 95-100%) but the magnitude estimates have very wide confidence intervals. Passing back +$256 for "Age 65+" when our actual estimate could plausibly be anywhere from +$80 to +$400 would tell Meta to overpay for senior audiences without confidence in the value. Until the cohort grows past ~30 whales per signal, fire the $187 Self-Pay baseline for every Self-Pay conversion. Track the watch list signals and re-evaluate at the next quarterly refresh.

Watch list — all Self-Pay signals DO NOT PASS BACK YET

"I'm ready" at signup QUIZ80% more likely to be a whale · 97% confident · supported by n=12 whales — closest to the n≥30 bar; likely the first to graduate to pass-back as the cohort grows
+80% lift
WATCH
Age 65+ QUIZ4.3× more likely to be a whale · 100% confident · supported by n=10 whales
4.3× lift
WATCH
Male gender QUIZ2.7× more likely to be a whale · 99% confident · supported by n=8 whales — only whale profile where men over-index, but tiny sample
2.7× lift
WATCH
Age 45-54 (minnow flag) QUIZ3× more likely to be a minnow · 97% confident · supported by n=6 minnows — too few observations to set a downlift value
3× minnow
WATCH
Lives in New York QUIZ4.5× more likely to be a whale · 98% confident · supported by n=4 whales — the lift estimate is statistically real but the dollar uplift could be off by hundreds in either direction
4.5× lift
WATCH

For now, every Self-Pay conversion fires at the $187 baseline. Re-run this analysis at 90 days; the Self-Pay cohort doubles roughly every 4-5 months at current run-rate, so "I'm ready" and Age 65+ should clear n≥30 by the next refresh after that.

Worked examples

Three customer profiles, three different passback values. This is what each conversion event would fire with under the current sample-size constraints.

Insurance · 6 signals
The Hopeful Returner archetype
35-44 woman on Aetna. At quiz time: sleeps 5-6 hrs, body recomp goal, "feeling hopeful," no anxiety, moderate stress. All six signals clear both the confidence and sample-size bars.
Baseline (Insurance)$112
+ Sleep 5-6 hrs (n=74)+$23
+ Aetna (n=31)+$23
+ No anxiety (n=36)+$22
+ Body recomp (n=51)+$19
+ Hopeful (n=46)+$18
+ Moderate stress (n=82)+$11
Pass back$228
Self-Pay · sample too small
The Subscription Senior archetype
67yo male in NY who said "I'm ready" at signup. Looks like the whale profile — but every Self-Pay signal is currently below n≥30. Pass back baseline only until cohort matures.
Baseline (Self-Pay)$187
~ Age 65+ (n=10, watch)
~ Lives in NY (n=4, watch)
~ Male (n=8, watch)
~ "I'm ready" (n=12, watch)
Pass back$187
Conservative — protects against Meta over-bidding for senior NY men based on a 4-whale estimate. Re-evaluate at 90 days.
Insurance · 0 signals
Generic conversion, no quiz data captured
Conversion fires before the quiz finishes, or with quiz answers that don't trigger any confirmed signal.
Baseline (Insurance)$112
(no signals)+$0
Pass back$112
Better than firing $0 — Meta still treats it as a real conversion at cohort-average value.

Don't pass back these signals

These look meaningful in the data, but they don't belong in the passback value. Each one either confuses the platform or isn't observable when conversion fires.

  • Channel signals (Google paid, Facebook paid). Meta and Google already know which platform delivered the conversion. Passing this back would double-count the channel effect and skew the platform's own attribution model.
  • Operational signals (weekly billing, sessions attended, no-show rate, claim reimbursement %). These aren't observable at conversion time. By the time you see them, the customer is already acquired and the ad spend is sunk.
  • Sub-95% confidence signals (Texas, Illinois, Cigna avoidance, Anthem-as-minnow flag, "feeling hopeful" as minnow protection). Some of these will turn out real, but the platform optimizer will treat noise as signal and waste budget chasing a phantom audience. Re-evaluate next quarter when the cohort matures.
  • Statistically significant signals with n<30 supporting whales (all Self-Pay signals, Insurance Age 55-64 protective). The lift estimate is real but the magnitude estimate is unstable — could be off by 2-3× in either direction. Track on the watch list, don't bid on yet.
  • Whale/minnow flags from the wrong cohort. Don't apply Insurance signal uplifts to a Self-Pay conversion — Aetna isn't relevant to a cash-pay client, and the lift values are calibrated against different baselines and ceilings. Check billing_type first, then apply the matching set.
Implementation note

Insurance VBB launches now. Self-Pay VBB launches when the cohort grows.

Insurance is ready. Seven signals clear both filters (95%+ confidence, n≥30 supporting whales). Wire these into the Meta and Google purchase events for Insurance conversions. Expected per-customer passback values will range from $112 (no signals captured) to ~$246 (full stack). The whale ceiling cap of $584 rarely binds because no realistic signal stack gets there.

Self-Pay isn't ready yet. All five Self-Pay signals are statistically real but supported by only 4-12 whales each. Fire the $187 baseline for every Self-Pay conversion until at least Age 65+ and "I'm ready" clear n≥30 (next refresh after 90 days, possibly the one after). Don't try to compensate by lowering the threshold to n=10 — that's how you end up over-paying for senior NY men based on a 4-whale estimate.

Validate within 6 weeks of going live. Check whether CAC for high-passback Insurance conversions ($200+) decreased relative to baseline conversions ($112). If yes, the platform is finding more whales. If no, the signal stack isn't moving bidding behavior — usually because high-value conversion volume is too low for the platform's ML to learn from. Broaden inclusion or feed the platform more conversions before expecting the optimization to kick in.

Top Nutrition Coaching · Whales & Minnows v5 · Safe cohort: tenure ≥ 3 months, n=1,869 · Signups Sep 1 2025 – Jan 20 2026 · Reference date Apr 22 2026 · mLTV = net revenue − ($60/hour dietitian labor on occurred + no-show + late-cancel appointments) · Confidence via Fisher's exact test